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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new context: it requires the applications:write scope and the Autopilot plan, and that text is stored verbatim in the form's own language. It does not explain what the destructive hint means in practice (i.e., whether existing answers are overwritten).

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?

Three tight sentences, front-loaded with what the tool does, then field semantics, then prerequisites. No filler; the only looseness is that the permissions/plan sentence sits last rather than being flagged as a precondition.

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 destructive write tool with a nested answers array, no output schema and no schema descriptions, the definition covers field semantics and access requirements reasonably well. It leaves out what happens on an unknown or invalid questionKey and what the response contains, which an agent would want before calling it.

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 0%, so the description must carry the parameter burden and it partially does: it maps question type to field (`text` for text questions, `choices` for radio/select/checkbox, `label` for live-form questions) and clarifies `text` is stored as given. It says nothing about `questionKey` or `applicationId`, or whether text and choices are mutually exclusive.

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 ('Saves answers for the application's questions') and immediately narrows scope: questions found on the live form need a label and get added. That distinguishes it from a pure draft-save, though it never names siblings like getfund_save_drafts or getfund_write_brain_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?

Implies when to use it via the 'question found on the live form' clause, which tells the agent this handles new/unknown questions. However there is no explicit when-not guidance and no comparison against the closely related sibling tools that also write answers.

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