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

The description adds substantial behavior beyond annotations: comments are internal-only, the call returns a job_id immediately, the AI pass takes 60–120 seconds in the background, duplicate in-flight calls cost extra, and COMMENT-level access is required.

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 purpose is front-loaded, and each sentence adds operational detail: status coverage, async return, result retrieval, duplicate-call cost, and access requirement. There is no empty filler.

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 async mutation, output schema, and access requirement, the description gives an agent everything needed to call it correctly: when to call, what it returns, how to retrieve the result, and the main cost/retry hazard.

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?

The description clarifies that the target is a post and that the call returns a job_id, but it does not explain the platform choice or the idempotency_key. The nested schema does document those fields, so this is adequate but not enriched much beyond structured data.

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 states a specific action and resource: analyse a post for virality and add internal team comments with improvement suggestions. It also distinguishes the async workflow from the sibling status tool by naming get_review_status(job_id).

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?

It explicitly says the tool works on drafts, scheduled, or published posts, explains that get_review_status is the read-only way to fetch results, and warns against duplicate concurrent calls because they run another AI pass and are charged again.

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