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

Beyond the annotations (readOnly, idempotent, destructive=false), the description discloses return behaviors: 'each claim comes back verified, violated, or out-of-scope, with the engine's computed value as proof and a decision-record hash tying the verdict to this spec version and these inputs.' It also emphasizes 'this tool never guesses,' a key behavioral trait not otherwise stated.

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 intentionally structured: opening with the main purpose, then instructions, return details, out-of-scope explanation, and usage guidance. Every sentence contributes new information without repetition or filler.

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?

No output schema exists, so the description carries the burden of explaining return values, which it does fully (verified/violated/out-of-scope, computed value, decision-record hash). It also covers the tool's closed-world principle ('never guesses') and differentiates from run_model, making the context complete for an agent to select and invoke it 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 coverage is 100%, so baseline is 3. The description adds meaningful context about the claims parameter structure ('{path, op, value}') and the verdict mapping (verified, violated, out-of-scope), which clarifies how claims are interpreted and what the result means. This goes beyond the schema definitions, especially given no output schema exists.

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+resource: 'Verify claims about a model's outputs against the engine before presenting them to a user.' It clearly states the tool's function and distinguishes it from siblings by contrasting with run_model ('use run_model when you want the full output envelope').

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?

Provides explicit when-to-use guidance: 'Use it to check a number you are about to state; use run_model when you want the full output envelope.' Also includes contextual timing ('before presenting them to a user') and explains the out-of-scope behavior, which informs when the tool is appropriate.

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