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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: it is deterministic, compares expected vs observed values, reports 'material differences' under caller-supplied rules, and is a paid resource with a specific price. It does not detail what 'material differences' means or how verification rules are supplied, but it adds value beyond the annotations.

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?

Three sentences, each earning its place: the first states the core function, the second gives the usage boundary, the third discloses the cost. The most important information is front-loaded. It could be slightly tighter, but there is no fluff.

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 comparison/verification tool with no output schema, the description covers the purpose, exclusions, and cost, but it does not explain the return format, how 'material differences' are reported, or the exact semantics of the optional parameters. Given the tool's moderate complexity (5 params, no output schema), the description is adequate but not complete enough for an agent to invoke it with full confidence about the result shape.

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 0%, so the description carries the burden of explaining parameters. It explains the two required parameters conceptually ('expected and observed values') and mentions 'caller-supplied verification rules' which maps to ignore_paths, required_paths, and numeric_tolerance. However, it does not explain the path syntax, how numeric_tolerance applies, or the semantics of ignore_paths vs required_paths. The description adds some meaning but leaves significant gaps for a 5-parameter tool with 0% schema coverage.

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 ('compares'), a clear resource (caller-supplied expected and observed values), and the core behavior (reports material differences under verification rules). It also distinguishes itself from adjudication tools by explicitly excluding legal/identity/sanctions/fraud/contractual/regulatory use. However, it doesn't explicitly differentiate from the many sibling verification tools (e.g., execution_safety_verification_*, outcome_assurance_verification_*), relying on the 'trust identity permission' domain in the name rather than a direct comparison.

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 gives clear context: it is intended for 'trust identity permission / quality unknown' and explicitly says 'Do not use for legal, identity, sanctions, fraud, contractual, or regulatory adjudication.' This provides a when-to-use and when-not-to-use boundary. It does not name a specific alternative tool, but the exclusion list plus the domain-specific name gives an agent enough routing guidance.

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