Check a checkout session

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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses concrete operational behavior: no carrier call, no quote allowance, nothing changes, 30-day session lifetime, session_not_found sentinel, no PII in responses, and a rate limit of 60 checks per hour. It also warns that polling too fast is useless because nothing moves until the human acts. This is rich behavioral disclosure that materially affects how an agent should call the 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?

The description is longer than average but every section earns its place: statuses, polling cadence, privacy, expiry, manual-review edge case, and rate limit. It is front-loaded with the core purpose and then logically organized into statuses and parameter rules. There is no filler or tautology.

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 is complete for an agent to call this tool correctly: it names the input source, explains every possible status, gives the error sentinel for bad ids, states the rate limit, clarifies privacy, and directs onward to track_parcel. The output schema exists, so return-value details are not the description's burden. No critical operational gap remains.

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?

Although the schema already covers session_id with a pattern and description, the description adds essential semantics: the id shape 'as_ plus a UUID', that nothing else identifies a session, that unknown/malformed/expired ids return session_not_found rather than a status, and that the id must be treated like a tracking number. This goes well beyond the schema and compensates fully for any ambiguity.

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 opens with a specific verb and resource: 'Reports where a payment session made by create_checkout_link stands.' It clearly distinguishes this tool from siblings by explaining it reads only SMKlog's own order records and later points to track_parcel for scan events. The status list further anchors what this tool does and what its output means.

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 gives explicit when-to-use guidance: 'Poll it after handing the human the link, minutes apart rather than seconds.' It also tells the agent when to switch to a sibling tool: 'Once label_ready, feed tracking_number to track_parcel for scan events.' It adds exclusions like the manual-review request not being a checkout, which prevents incorrect invocation.

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