The core tool specs and workflows are efficient and domain-specific, but the body pads in background Claude already knows ('TEM resolves individual protein complexes (~2nm). Cryo-EM achieves near-atomic resolution (<4Å)... SEM shows surface topology.'), repeats resolution bands across three sections, and devotes a long inline aside to the tangential IDR resource.

Each phase names concrete tools with exact input parameters and output fields, and a runnable `tu.run_tool("IDR_search_studies", {...})` example appears — but the six core EM phases give only prose input/output specs with no executable call examples, leaving the main pipeline not copy-paste ready.

A clear 8-phase sequence with an overview diagram and per-phase numbered steps, plus a quality-assessment checklist, fitting-quality indicators, and edge-case fallbacks (e.g., no EMDB entries → PDB method filter) that serve as error recovery; the read-only nature means the destructive-operation cap does not apply.

Internally well-organized with clear headers and tables, but it is a single ~290-line monolithic file with no bundle files or one-level-deep references; content such as the detailed per-phase tool specs and the lengthy IDR aside could be split into separate reference files.

Lists multiple concrete actions across named resources — 'Search and analyze electron microscopy data', 'finding 3D structural data', 'comparing experimental EM resolution to AlphaFold confidence', 'accessing raw EM data for re-processing' — naming EMDB, PDB, EMPIAR, and CryoET Data Portal specifically.

Clearly answers both what ('Search and analyze electron microscopy data — ...') and when via an explicit 'Use for finding..., comparing..., and accessing...' trigger clause; not capped at 2 because the trigger guidance is explicit.

Strong coverage of natural terms a structural-biology user would say: 'cryo-EM', 'EMDB', 'PDB', 'EMPIAR', 'cryo-electron tomography', 'raw micrograph datasets', 'AlphaFold confidence', and 're-processing'.

Tightly scoped to electron-microscopy modalities (cryo-EM maps, tomography, micrographs) with distinct database triggers, clearly separate from X-ray/NMR structure search or protein-structure prediction skills.