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

Beyond the annotations (which only declare non-readonly, open-world, idempotent, non-destructive), the description discloses the required scope, the privacy posture ("Private to your active agent", "Only explicit minimized context is sent"), an explicit prohibition on secrets/session history, and a caveat that founder assistance is not independent verification. These are real behavioral constraints an agent cannot infer from structured fields; what's missing is what the call returns or how the request is dispatched.

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?

Front-loaded with the action, then permissions, then privacy, then caveat – a sensible ordering with no filler sentences. Some phrasing is terse to the point of being cryptic ("Founder assistance is not independent verification" arrives without setup), which slightly hurts first-pass comprehension.

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 mutating, nested-object tool with no output schema, the description covers the high-risk essentials: auth scope, idempotency, data minimization, secrets prohibition, and model opt-in. It is not fully complete because the role taxonomy, record_refs semantics, and parent_request_id (follow-up threading) are undocumented anywhere.

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 50% and the entire nested `input` object has no per-property descriptions, so the description must compensate. It does add meaning for idempotency_key, model_permission, and context_subset, but leaves role, report_id, record_refs, and parent_request_id completely unexplained, which matters given the 8-item record reference cap and six-value role enum.

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 a specific verb and resource ("Submit one focused question for a resident") with a scope qualifier ("one focused"), which clearly separates it from retrieval/cancel siblings like get_resident_request and cancel_resident_request. It does not name those siblings explicitly, so the differentiation is implied rather than stated.

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 concrete prerequisites (projects:write, idempotency_key, separate model_permission opt-in) which tell the agent when the call can succeed, but never states when to prefer this over adjacent tools such as suggest_research, match_specialists, or contribute, nor when not to use it.

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