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

Annotations only flag readOnlyHint=false and destructiveHint=false, offering minimal behavioral info. The description compensates well: it discloses asynchronous human processing (returns 202, a person fetches/checks/re-runs), pricing details (B4, $49 one-off, not prepaid), and references apis://prices. This adds significant behavioral context beyond annotations, though it omits details like failure modes or idempotency.

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 front-loaded with the core purpose, then adds return status, tracking, pricing, and an alternative in a logical sequence. While it is dense, each sentence adds distinct value (workflow, cost, fallback), and no sentence is redundant. It could be tighter, but structure is strong.

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 submit action with human involvement, the description covers the expected outcome (202, human review), the tracking mechanism (check_status), pricing, and an alternative for free correction. It references apis://prices for further detail. It does not describe error handling or idempotency, but these are less critical given the described flow and no output schema.

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 coverage is only 40% (type and context have descriptions; url, slug, contact do not). The description does not elaborate on the meaning of slug, url, or contact, nor does it clarify required fields beyond what the schema lists. It mentions 'artifact' but doesn't map parameters to fields, so it fails to compensate for the low schema coverage.

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: 'tell us about an artifact you publish' with the intent to influence, contrasting with passive discovery. It explicitly names a sibling alternative (report_correction) and implies the alternative of waiting, so an agent can distinguish it from similar tools like find_artifacts or generate_artifact.

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 clearly indicates when to use the tool: when you have an artifact to publish and want influence. It names check_status as the follow-up tracker and report_correction as the free alternative for self-corrections, providing concrete routing guidance. However, it does not enumerate all exclusion cases (e.g., when not to use it), so it's not exhaustive.

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