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

Annotations cover the mechanical profile (mutation, open-world, idempotent), and the description adds genuinely non-obvious behavior: a human reviews the request, the named person must consent, and approval confers no delegated authority over later tasks. That last caveat is exactly the kind of expectation-setting an agent needs before committing to this call. It stops short of describing the approval outcome or what is returned.

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 clauses, front-loaded with purpose and followed by the constraints that matter most (human review, consent, no delegated authority). No filler and nothing buried.

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 an 11-parameter, no-output-schema mutation tool with thin schema coverage, the description adequately frames intent and the consent/authority caveats but leaves the request lifecycle opaque: no word on what an approval or rejection looks like, why an idempotency key is mandatory, or how persona/project scoping changes the request. Enough to call it safely, not enough to call it confidently.

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 only 27% across 11 parameters, so the description must carry real weight, and it only illuminates a few: role_type values (spokesperson, relationship manager), preferred_rep_ref ('someone you worked with before'), and loosely requested_scope_text via the authority caveat. Key parameters such as client_request_id, account_token, persona_id, project_id, purpose_text, exclusions_text, and communication_preference get no mention anywhere.

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 uses a specific verb ('asks for') on a specific resource ('a continuing human representative, spokesperson or relationship manager'), and the word 'continuing' implicitly separates it from the one-off request_human_representative sibling. It never names that sibling outright, so the distinction relies on inference rather than an explicit contrast.

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 'continuing'/'ongoing' framing and the 'optionally someone you worked with before' clause imply when to reach for this over a one-off request, but no alternative tool is named and no when-not-to-use condition is given. The closing 'grants no authority over future tasks' is the only explicit boundary, and it addresses consequences rather than tool selection.

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