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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds valuable behavioral context beyond that: the comparison is deterministic, differences are materiality-filtered, and verification rules are caller-supplied. It could disclose result format or edge-case behavior, but it adds meaningful non-annotation information.

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 compact sentences with no filler. Core behavior is front-loaded, exclusions follow, and the paid-resource cost/price is a useful operational detail. Every sentence earns its place.

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 five parameters, zero schema parameter descriptions, and no output schema, the description is too thin. It clarifies intent and exclusions but omits essential invocation semantics such as how ignore_paths and required_paths are expressed, what numeric_tolerance applies to, and what the returned 'material differences' report looks like. An agent could select the tool but would likely struggle to call 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 description coverage is 0%, so the description must compensate. It explains 'expected' and 'observed' as values to compare, but gives no guidance on ignore_paths, required_paths, or numeric_tolerance semantics, despite these being central to 'caller-supplied verification rules.' The parameter names are suggestive but not defined, leaving an agent to guess about path formats and tolerance behavior.

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... and reports material differences') with a clear resource: caller-supplied expected and observed values. It identifies its domain as reliability quality/execution risk, which helps distinguish it from adjacent verification tools, though it does not explicitly name a sibling to differentiate from.

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 explicit intended use ('Intended for reliability quality / execution risk') and explicit exclusions ('Do not use for legal, identity, sanctions, fraud, contractual, or regulatory adjudication'). It stops short of naming alternative tools for those excluded cases, but the when-not-to-use guidance is clear.

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