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

Annotations already declare openWorldHint=true and destructiveHint=false, and the description reinforces this with the public-publication authorization requirement and the explicit 'does not buy anything or bypass access controls' disclaimer. It also adds PII/content restrictions and idempotency-key reuse guidance not present in annotations. Minor tension: it instructs key reuse for retries while idempotentHint is false, but this is not a direct contradiction — the annotation reflects that a naive repeat call can still create a new report.

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?

Compact and front-loaded: the core action and authorization requirement come first, followed by prohibitions and operational rules. Every sentence carries content; only the 'does not buy anything' clause partially restates what the description already implies.

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 16-parameter, no-output-schema tool with 6% schema coverage, the description covers policy and safety well but leaves the data contract largely unexplained — no guidance on what a valid 'summary', 'details', or 'domain' should contain, nor on the size limits already encoded in the schema. Adequate for calling safely and honestly, but not complete for calling correctly.

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 only 6% (just idempotencyKey), so the description must compensate for 15 mostly undocumented parameters, and it does not. It clarifies inferenceEffort ('unknown if unmeasured') and idempotencyKey reuse, and its PII prohibitions indirectly constrain summary/details, but domain, summary, attemptedAt, agentName, agentVersion, countryCode, tokens, durationSeconds and paymentMethod are all left without meaning. The enum parameters are self-documenting via their values, which keeps this above a 1.

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 and resource — 'Publish an observed purchase attempt after success, failure or abandonment' — which is far more informative than the name 'submit_review' or the title. It is distinguishable from read-side siblings (list_reviews, get_merchant), though it never explicitly says it is the write counterpart to list_reviews, and the name/description mismatch (review vs. checkout-attempt report) adds a small ambiguity.

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 when-not conditions ('Do not invent attempts', do not publish card data/credentials/order IDs) plus operational rules (reuse idempotencyKey on retries, set inferenceEffort to unknown if unmeasured). It also scopes the tool negatively ('does not buy anything or bypass access controls'). What is missing is any explicit pointer to list_reviews for reading reports back.

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