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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=true): it discloses the persistent side effect (answers saved to the application as the founder's answers), that the run resumes and continues afterward, the conflict failure mode, the required scopes (applications:write and Autopilot plan), and the return shape. That is exactly the missing-risk context an agent needs before writing.

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?

Dense and front-loaded: the trigger condition, payload forms, side effect, and prerequisites arrive in a compact sequence with no filler. The long compound sentences make it slightly harder to parse than it needs to be, but every clause adds information.

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?

Covers purpose, preconditions, destructive effect, auth requirements, error behavior, and return shape for a non-idempotent mutation with no output schema. Minor gaps remain: whether all missing answers must be supplied at once, and how partial or malformed answers are handled.

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 carries the burden and mostly does: it explains that each answer is keyed by questionKey, that `text` is for text questions and must be in the form's own language, and that `choices` takes option labels for choice questions. It leaves runId and loose constraints (max 30 answers) unexplained, so not fully compensating.

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 ('Answers the questions a hosted run waits for') plus the exact trigger state (`waiting_founder` with `reason missing_answer`). This distinguishes it from the answer-adjacent siblings (draft_answers, save_answers, approve_answers) by making clear it targets a paused run rather than a stored submission.

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 an explicit precondition (run must be waiting for a missing answer) and an explicit non-applicable case ('a run waiting for anything else answers conflict'). It does not, however, route the agent to siblings such as getfund_save_answers or getfund_draft_answers when no run is waiting, so the alternative-selection guidance is incomplete.

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