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

The description adds substantial behavior beyond the annotations: stale checks trigger a rate-limited background check, only one check runs per deal at a time, and a pending result includes retry timing. It also clarifies the important semantic limits that a check never proves a coupon works and a failed check never marks a deal verified.

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 dense but front-loads the main purpose and then covers side effects, pending behavior, status meanings, and limitations. Every sentence contributes useful information, though the text could be slightly easier to scan.

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?

Given the existing output schema and annotations, the description supplies the remaining behavior an agent needs: background check queuing, rate limiting, retry behavior, status meanings, and verification caveats. Nothing essential for correct invocation appears to be missing.

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 schema fully documents the sole deal_id parameter, including its pattern and source. The description adds a useful constraint by clarifying that the tool takes a deal id and never an address.

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 this returns the status of one stored deal, including lifecycle, latest check details, and freshness. It distinguishes itself from search-style tools by requiring a single deal id, but it does not explicitly contrast with the sibling get_deal.

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 explains what to do when the latest check is not fresh: the tool queues a background check and returns pending with retry_after_seconds, so the caller should call again later. It also explains not_checkable and unavailable outcomes. It lacks explicit guidance on when to use this instead of get_deal.

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