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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile needs no restating. The description adds genuinely non-obvious behavior: an eligibility gate, the fact that returned results are short-lived links rather than documents, and the 'idcard:<policy_id>' pseudo-identifier. The expiry window and whether listing is paginated are left unstated.

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 with no filler, each carrying a distinct fact: eligibility, list mode, link mode. The 'Current clients only' gate is placed first, which is a defensible ordering for a client-scoped tool.

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 two-parameter read tool with no output schema, the description covers the behavior an agent needs to choose a call correctly, including the dual return shape. The remaining hole is operational: how to supply or obtain client_session, and how long the returned link stays valid.

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 0%, so the description must carry parameter meaning, and it does well for document_id by explaining both of its modes and a special string form. client_session, a required parameter, gets no explanation at all — nothing about what session value is expected or how to obtain one. Coverage is therefore half the job.

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?

States the resource (policy documents and auto ID cards) and splits behavior explicitly by input: no document_id lists documents, with document_id returns a short-lived link. That is far more than the title's 'Get a policy document' implies. It stops short of naming a sibling it should be preferred over (e.g. get_policy_details or list_my_policies), so differentiation is left partly to inference.

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?

Gives a clear precondition ('Current clients only') and a mode-selection rule tied to document_id, which is the main decision an agent faces. It does not say when to reach for another tool instead, nor what to do if the client is not signed in, so no exclusions or alternatives are offered.

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