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

Annotations only indicate non-read-only, non-idempotent, and open-world. The description adds significant behavioral disclosures: asynchronous processing, job reference return, no charge for already-tracked profiles, automatic refund on failure, and cost of 40 credits. No contradiction with annotations.

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 compact and front-loaded, with the primary action and scope in the first sentence. Each subsequent sentence adds essential operational detail (async, return type, duplicate handling, refunds, cost) without extraneous words.

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?

The description covers the crawling scope, asynchronous job reference, duplicate behavior, cost, and failure refunds. The only minor gap is not specifying what exactly is returned when the profile is already tracked, but the overall information is sufficient for a complex tool.

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 input schema has bare properties (handle, platform) with no descriptions, and schema description coverage is 0%. The description provides no additional meaning for the handle format or platform choices beyond the enum, failing to compensate for the lack of schema documentation.

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 clearly states a specific action ('Submits a public profile for crawling') and defines what is included: profile metadata, recent posts, stats, and thumbnails. It also distinguishes the tool by explaining the post-crawl behavior (stays tracked and appears in searches), setting it apart from siblings like get_profile or track_profile.

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 clear context: asynchronous execution, use with get_job_status, immediate return for already-tracked profiles, and credit cost. It does not explicitly name alternative tools for scenarios like simply fetching a profile, but the use case is well implied.

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