Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the description is free to add value elsewhere, and it does: data source (UniProtKB cross-references to the PDB), result ordering (best resolution first), aggregation behavior (counts by method), the experimental-only scope boundary, and a cost of 1 credit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is front-loaded: verb, resource, ordering and returned fields come first, then use case, then source and scope exclusions. The attribution phrase 'UniProt Consortium' and the cost suffix are low-value but short, and no sentence is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of describing return values, and it does so explicitly: method, resolution in angstroms, chain coverage, and per-method counts. Scope boundaries (experimental only, no ligands), ordering and cost are all stated, leaving nothing an agent needs before calling it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both limit (1-100, default 25) and accession documented, including a pointer to protein_for_gene inside the accession field. The description adds no parameter-level detail beyond the ordering note ('best resolution first'), so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'List the experimentally solved 3D structures (Protein Data Bank entries) for a protein'. It also names the exact returned fields (method, resolution in angstroms, chain coverage, counts by method), which separates it cleanly from siblings like protein_sequence or protein_for_gene.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete use case ('is there a crystal structure of X' for structural biology and drug-discovery work) and an explicit exclusion: AlphaFold predicted models and ligand details are not included. It also routes the agent to protein_for_gene for gene-symbol-to-accession resolution, though it does not name any alternative tool for retrieving predicted models.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.