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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the resulting state (stored as Claimed), cost model (free, verify costs 1 credit), the 30-day free re-check window, idempotency ('recording the same URL again updates it'), and the https-only constraint. It omits auth/permission requirements and failure behavior, but the disclosed traits are unusually rich for a create tool.

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?

A single dense paragraph with the core purpose front-loaded and every clause carrying information (constraints, cost, lifecycle, idempotency). It is efficient but verges on a run-on, and the per-kind url/liveUrl mapping would be easier to parse as a list.

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 6-parameter, 4-required tool with a nested meta object and no output schema, the description covers purpose, cost, lifecycle and idempotency but leaves the module enum semantics and most of the meta object undocumented. An agent could still call it, but would likely guess at module values and meta contents.

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 and it only partially does: it clarifies url vs liveUrl semantics for several kinds and documents meta.fixIds for site fixes. However, the module enum (FIXES, CONTENT, INDEX, LISTINGS, etc.) is never explained, the kind enum is only partially mapped to the examples, and meta's broader structure is left unaddressed.

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 (report/record) and resource (shipped work), then enumerates the concrete artifact types it accepts (PR, live page, listing, index request, post, Gmail draft), which lets an agent match its own artifact to the tool. It does not explicitly distinguish itself from the close sibling record_access, which handles a different recording flow.

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?

Gives clear context for when to call it ('report anything you shipped') and names the follow-up alternative (verify to check the claim, at 1 credit) versus the free automatic daily re-checks. It lacks any explicit when-not-to-use guidance relative to record_access or shipped, but the conditional mapping of url vs liveUrl per artifact type is strong usage guidance.

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