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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld). The description adds genuinely non-obvious behavior: check numbers are never returned, and private notes appear only when include_private_notes is set. The 'GET /payments' hint confirms the read path. It stops short of describing result shape or default ordering beyond what the schema says.

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?

Three tight sentences: identity and returned fields first, filters second, behavioral caveats last. No filler, no restatement of the title, every clause carries load.

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 10-parameter, no-output-schema list tool, the description covers returned fields, filter dimensions, and the two surprising behavioral facts. Pagination and sort details live in the schema rather than the description, which is acceptable given the 80% schema coverage.

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 coverage is 80%, so the baseline is 3; the description goes slightly beyond by summarizing the filter surface (client, project, id, date range) and by documenting the conditional semantics of include_private_notes and the intentional omission of check numbers. Notably client_id and project_id carry no schema description and are only covered here.

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?

Opens with a specific verb+resource ('List payments') and enumerates the returned fields (client, project, amount, date, type, method, public note), so the agent knows exactly what this returns. It does not explicitly name or contrast with sibling list tools, but the payment-specific field list makes ambiguity with list_invoices/list_expenses unlikely.

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?

States the filterable dimensions ('Filter by client, project, id or payment date range') and gives explicit conditional guidance for include_private_notes ('Only set it when the user asks for internal notes'). No alternative tools are named or excluded, but the context for invoking it is clear.

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