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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint, so the safety profile needs no restating. The description adds that results are database-annotated residues scoped to a domain, which hints that coverage depends on the member database and that only annotated positions come back. It does not mention that entries lacking domain annotations return nothing, which is the main behavioural surprise here.

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?

A single sentence with no filler, and the object of the lookup is front-loaded. Minor deductions: it is a noun phrase with no verb, and the capitalised 'INSIDE' is a stylistic emphasis that adds little.

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?

An output schema and annotations are present, so return shape and safety need not be described. What is missing is the practical context an agent needs before calling: that the accession must be an entry with member-database annotations, and how this differs from scanning domains or fetching a protein record.

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% and the accession field already explains the current-sequence numbering requirement in detail, so the description cannot add much. Its contribution is limited to framing the lookup as applying to a 'known protein', with no further elucidation of accession, _subject or _files.

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 names a specific resource — catalytic, substrate-binding, metal-binding and interface residues annotated by member databases within a domain — which is clearly residue-level annotation rather than domain scanning. It never uses an explicit verb ('returns'/'lists') and does not name the neighbouring tools (scan_protein_domains, lookup_protein), but the content is distinctive enough that an agent can separate it from those siblings.

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?

The only usage signal is the trailing phrase 'for a known protein', which implies an accession-bearing entry rather than a raw sequence. There is no statement of when this tool should be preferred over scan_protein_domains or lookup_protein, no prerequisites, and no exclusion conditions.

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