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

With annotations already covering the safety profile (idempotentHint=true, destructiveHint=false), the description still adds real behavioral context beyond them: the dedup behavior ('a drafting job already queued or running comes back instead of a second one'), the exact return shape including queue position and progress counters, the conflict condition when all answers are written, rate-limit exhaustion of daily drafting units, and required permission plus plan. It stops short of covering timing/duration of a drafting job, which keeps it at 4 rather than 5.

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?

The content is high-value and front-loaded with the core action, but the phrasing is dense and run-on in places, e.g. 'With every answer written it answers conflict, and once today's drafting units are used up, rate_limited,' which takes a re-read to parse. The nesting of conditions into single long sentences slightly hurts scannability, though little is genuinely redundant.

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 mutation tool with no output schema, the description is unusually complete: it covers what is and is not modified, idempotent re-queue behavior, all returned fields (application status, queued, draft with queue position, progress counters), and the failure modes conflict and rate_limited, plus auth and plan prerequisites. An agent can call it and interpret the response without opening other docs.

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% and there is one required parameter, applicationId, whose format (UUID) only appears in the schema. The description frames the parameter conceptually as 'the application' but never clarifies that a UUID is expected, where to obtain it, or its relationship to the returned application status, so it only partially compensates for the coverage gap.

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 names a specific verb and resource ('queues getfund's drafter for the application') and precisely delimits the scope of work: every question without an answer, with a gap, with issues, or with a stale draft is drafted, while the founder's own and approved answers stay untouched. The 'draft button on getfund' analogy plus the explicit note that drafts land as new versions with status draft or gap makes it distinguishable from siblings like getfund_save_drafts and getfund_approve_answers.

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?

Usage is implied through the 'way the draft button on getfund does' analogy and the stated prerequisites (applications:write and the Autopilot plan), and the description explains what happens when a job is already queued. However, it never names an alternative tool or states explicitly when to prefer this over getfund_save_drafts, getfund_write_brain_answers, or getfund_approve_answers, so the agent must infer the routing.

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