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

Annotations are minimal (readOnlyHint false, destructiveHint false), so the description carries the burden of behavioral disclosure. It states 'Requires act scope; no spend or posting' and 'keeps evidence holds and never authorises drafting,' which are useful constraints. However, it's ambiguous what 'keeps evidence holds' means and doesn't fully explain side effects like whether existing data is modified. It adds some value beyond annotations but not comprehensive.

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 description is a single dense paragraph that mixes operational rules, constraints, and parameter notes without structure. It's over 200 words, front-loads the purpose but then rambles through exceptions and conditions. It would benefit from bullet points or separation by operation. Every sentence carries weight, but the lack of organization makes it hard to parse.

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?

Given the tool's complexity (14 params, nested objects, 3 operations, no output schema), the description is incomplete. It covers the three operations and some constraints but doesn't explain critical parameters like why, text, title, channel, idea_id, claim_ids, or the structure of research and source_idea. It also doesn't mention return values or error conditions. An agent would struggle to build a correct request without consulting additional resources.

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?

With schema description coverage at 0%, the description must compensate for all 14 parameters. It only mentions a handful (run_key, action_kind, source_url, adopt_legacy, expected_updated_at) and leaves others like why, text, title, channel, idea_id, research, claim_ids, and source_idea unexplained. The description gives partial semantics for some operations but fails to define the majority of parameters, making it insufficient for correct invocation.

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 opens with 'File a growth idea (optional channels, kind, score), original X draft or research outcome,' which clearly states the tool's main function: creating content records of three types (idea, draft, research). It distinguishes from siblings like record_claim and record_insight by focusing on content creation rather than claims or insights, though it doesn't explicitly name alternatives. The purpose is specific enough to be actionable.

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?

The description provides operation-specific guidance: research appends results to an idea, drafts require action_kind social_post and one idea_id or source_idea, adopt_legacy reclassifies an exact saved replay, and completion uses move verbs. It explains when each operation is appropriate, though it doesn't explicitly mention when not to use the tool or name sibling tools as alternatives. The guidance is clear and contextual.

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