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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds real value on top by disclosing the conflict-resolution outcome (existing answers preserved and returned in skipped_existing, or overwritten when replace is set) and the required permission scope and plan tier. It stops short of describing error behavior or batch limits.

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 with no filler; the default-vs-replace semantics are front-loaded and prerequisites appended last. Efficient, though the phrasing 'replaced result' is slightly terse.

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?

With no output schema, the description carries return-value burden and does partially cover it via skipped_existing and the replaced result. Missing details like batch size limits and what skipped_existing entries contain are minor given schema-enforced constraints.

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 must compensate. It clarifies `replace` (default false, overwrites when true) and `locale` ('the language the text is written in'), but leaves `key`, `text`, `applicationId`, and `startupId` undocumented.

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: 'Writes answers to the startup's brain keys'. An agent can tell this apart from generic save/draft tools by the 'brain keys' scope, though it does not explicitly name the sibling alternatives (getfund_save_answers, getfund_draft_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?

Explains the default behavior (existing answers kept, listed in skipped_existing) and the override condition (`replace: true`), plus prerequisites (brain:write, Autopilot plan). However it gives no guidance on when to choose this over getfund_save_answers or getfund_draft_answers.

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