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

The description adds behavioral context beyond the annotations: it states the tool does not fetch pages, does not establish source availability, and involves no payment. These are important behavioral traits not captured by readOnlyHint or idempotentHint alone. It does not contradict any annotation. This extra context is valuable for an agent deciding whether to invoke this 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 two sentences with zero redundancy. The primary action and scope are front-loaded in the first sentence, and the exclusions are efficiently stated in the second. Every word earns its place, making it highly concise and easy to parse.

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 tool with only two parameters (one nested) and a rich input schema, the description covers the essential purpose and exclusions. It does not mention return values or error behavior, but since there is no output schema and the tool is read-only, that is not critical. The description adequately complements the schema and annotations to give an agent the necessary context to invoke the tool 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 50% (only requireAllSources has a direct description; sources lacks one). The description partially compensates by describing the operation on 'bounded URLs and literal quotes', which gives meaning to the sources parameter. However, it does not explain requireAllSources beyond what the schema already provides. The item-level descriptions for url and quotes are detailed, so the overall parameter semantics are reasonably covered, but the description itself adds limited unique value 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 states a specific action (check bounded URLs and literal quotes against a fixed host list) with clear scope and context (before purchase). It also explicitly disclaims what it does not do (fetch pages, establish availability, payment), which distinguishes it from other tools that might perform those actions. This clearly differentiates it from siblings like audit_report_citations or compare_evidence_snapshots.

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 provides clear usage context by stating 'before purchase' and clarifies what it does not do, which implicitly tells an agent not to use this tool for fetching or payment. However, it does not explicitly name alternative tools or provide when-not-to-use conditions relative to siblings like validate_batch or prepare_evidence_request. The context is clear but lacks explicit exclusions or alternative routing.

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