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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds substantial behavioral context beyond annotations: it explains the bounded nature of NOT FOUND, that CLOSE MATCH lists differing tokens rather than a similarity number, that no model is consulted, and that audio requiring transcription returns CAN'T ESTABLISH with acquisition_required. This is rich, non-obvious behavior that an agent needs to interpret verdicts correctly.

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 and information-rich, front-loading the verdict taxonomy and then adding behavioral caveats. Every sentence earns its place, though the length is substantial. It is structured logically: verdicts first, then evidence details, then limitations and exclusions. Slightly long but justified by the complexity of the tool's output semantics.

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 2 parameters, no output schema, and complex verdict semantics, the description is remarkably complete. It covers all verdicts, the evidence returned, the scope of inspection, the handling of different source types, and the exclusion of audio requiring transcription. An agent has everything needed to call the tool correctly and interpret its results.

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 coverage is 100%, so the schema already documents both parameters. The description adds meaning by explaining that 'statement' is 'one claim at a time, up to 600 characters' and that 'source' is 'the public http(s) link the statement is supposed to come from.' It also clarifies the relationship between the two parameters: the source is what the statement is checked against. This goes beyond the schema's field descriptions.

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 verb ('check') and resource (a statement against a source), and enumerates the five verdicts with precise definitions. It distinguishes itself from sibling tools by describing the full verdict taxonomy and the bounded nature of NOT FOUND, which no sibling name suggests.

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 explicitly says when to use this tool: for checking a statement against a source, and when not: audio needing transcription should be yanked first, and sources Yank already holds check immediately. It also clarifies that no model is consulted and that verdicts are not truth judgments, which prevents misuse.

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