Gather the digitised documents attached to a record

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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses that the server never requests gallica.bnf.fr and therefore reports nothing about document accessibility, content, or reuse terms. It also defines 'depiction', 'reproduction', and 'ocr' and states it does not fetch OCR content. This is rich behavioral context that annotations alone do not provide.

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 description is long and dense, but all sentences contribute meaningful information about behavior, limitations, or usage. It is front-loaded with the core purpose. It earns a high score for value, though it could be shortened or broken into clearer sections without losing substance.

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?

The tool is complex (handles two record types, returns typed links, has external limitations), and the description covers all relevant aspects: how it traverses editions for works, how it handles persons, what it returns (links only), what it does not report, and the meaning of result categories. With an output schema present, the description is fully adequate for an agent to select and invoke the tool correctly.

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?

The input schema already describes id and kind, and the description reinforces this by explaining that id may be a person or work identifier and that kind 'auto' costs an extra query. However, the 'limit' parameter is not mentioned in the description, leaving a minor gap despite its schema constraints (min, max, default). This is a slight shortfall given schema coverage is 67%.

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 clearly states the tool gathers digitised documents attached to a person or work and returns them as links. It distinguishes itself from list_editions by explicitly saying when to use that sibling tool. The verb 'Gather' and resource 'digitised documents' are specific and unambiguous.

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 description gives explicit usage guidance: it says 'Use list_editions when which edition a copy belongs to matters' and explains how the tool handles work vs person records. It also notes that the 'auto' kind option costs an extra query, helping the agent decide when to avoid it. These are clear when-to-use and when-not-to-use signals.

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