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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=true, so the safety and scope profile are covered. The description adds only that queries can be company-wide or per-candidate, which is consistent with openWorld. It says nothing about pagination behavior or return shape, so it is adequate but not rich.

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?

Two compact sentences with the resource and scope stated first, then a pointer to more detailed argument docs. Little waste, though the get_tool_reference pointer is a slightly unusual indirection.

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?

With a full input schema, an output schema, and rich annotations, the description covers what an agent needs in order to call it correctly. Only minor gaps (return format, pagination) remain, and those are largely carried by the output schema.

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 100%, so every parameter is documented in structured form; the baseline of 3 applies. The description adds a little meaning for attention=true and candidate scoping, but then defers full argument detail to get_tool_reference rather than compensating itself.

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 tag [Document requests] and a clear statement of the resource: documents asked from candidates, with the scope options (company-wide vs. one candidate). It's distinguishable from write-side siblings like request_candidate_documents or update_document_request, though it doesn't name them explicitly.

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?

It explains the filtering levers (by status, by candidate, attention=true) and clarifies that attention surfaces the ones that need a look (uploaded, overdue). It stops short of saying when to prefer this over update_document_request or request_candidate_documents, and gives no exclusions.

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