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

Beyond the readOnlyHint annotation, the description adds meaningful behavior: documents never create bookings, results are limited to the newest rows, total_count may exceed files.length, and match_ambiguous items await a decision with proposal details. This gives the agent crucial expectations about side effects and pagination that annotations alone do not convey.

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 dense but every sentence and clause carries useful information, from the row definition to the status pipeline to the no-booking guarantee. It is front-loaded with a plain statement of what the tool does before diving into status semantics.

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?

For a list-and-filter tool with an output schema, the description is complete enough to call correctly: it covers result ordering, limit cap, status filters, proposal resolution, and side-effect constraints. The agent knows how to navigate the result set and what follow-up action to take.

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?

Although schema coverage is 100%, the description substantially expands parameter meaning. It explains each status enum value in pipeline terms, details proposal.reason values such as multi_candidate and dkim_fail, and clarifies the limit's 'newest first' behavior and capped maximum.

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: 'Lists the organisation's captured documents', clarifying each row is a stored artifact and that results are newest first. It distinguishes the tool's role from bank-record tools by stating documents are evidence and 'NEVER create bookings'.

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 clear operational guidance: use the status filter to reach older rows beyond the newest limit, and resolve match_ambiguous proposals by calling attach_document. It does not explicitly name sibling tools to avoid, but the workflow context is strong enough for an agent to know when this listing tool is appropriate.

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