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

Annotations already declare read-only, non-destructive, and not open-world, but the description adds meaningful behavioral detail: the strict evidence threshold for CONFIRMED, the fallback to UNKNOWN, and the inclusion of a proof packet. This goes beyond the annotations and gives agents a clear expectation of outcomes and reasoning.

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 compact and front-loaded, with the core action and output stated first. The second sentence clarifies the critical evidence rule, and the third provides operational context (sandbox availability). Every sentence earns its place; no filler or redundancy.

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 moderate complexity of document parsing and reconciliation, the description covers the input, the verdict states, the evidence rule, and the proof packet. With an output schema present, the return structure is likely captured there. Minor gaps include lack of mention of error handling or multi-document merging, but these are not critical for a read-only tool with such a focused scope.

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 single parameter 'documents' is fully described in the input schema (100% coverage), so the baseline is 3. The description adds no additional semantics about the parameter structure or content, relying entirely on the schema. It doesn't explicitly state how the documents array is used or what constitutes valid input beyond the schema.

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 the verb 'parse' and resource 'booking/confirmation documents', and specifies the exact output (verdicts with proof packets). It also clarifies the nuanced CONFIRMED vs UNKNOWN rule, so an agent knows precisely what the tool does. Though it doesn't explicitly differentiate from the sibling, the purpose is unmistakably clear.

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 implies usage by stating it parses booking documents, but it gives no explicit guidance on when to use this tool over the sibling 'supplier_coverage'. No when-not-to-use conditions or alternative selection criteria are provided, leaving the routing decision to inference.

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