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

Annotations already cover the safety profile (readOnly, non-destructive, openWorldHint=false), yet the description adds substantive behavioral disclosure beyond them: no provider calls, no URL fetching, no persistence, and no claim to establish current inclusion beyond the supplied observations. The last point is genuinely important, since it warns the agent not to treat the output as a live visibility measurement.

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?

Two sentences, with the positive statement of function front-loaded and the constraints following. The disclaimer sentence is long but every clause does work by closing off a plausible agent misreading. Minor cost: the negative framing dominates the description's length.

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?

An output schema exists, so return-value explanation is unnecessary. The description correctly establishes the input source and boundaries, but omits how non-completed observations (the error/skipped variant in the schema) affect the computed rates, and does not indicate the scope or time basis of the calculation. Adequate but with a real gap for a tool whose only job is deriving rates.

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%, so the schema partially documents the observation fields (sourceLabel, surfaceType, observedAt, businessCitationUrls). The description links the output to two of those concepts ('mention' and 'business-citation' rates), adding some interpretive value, but says nothing about businessName or how the completed vs. error/skipped observation variants are treated. Roughly baseline for this coverage level.

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 first sentence states a specific verb and resource: 'Calculate mention and business-citation rates from caller-supplied captures.' That is concrete enough to distinguish it from siblings like build_visibility_action_plan, which build plans rather than compute rates. It does not, however, explicitly name or contrast itself against either sibling.

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?

Usage context is implied rather than stated: 'caller-supplied captures' tells the agent this tool consumes data the agent already holds, and the exclusions ('does not call AI providers, fetch URLs') rule out the expectation of live scanning. But there is no explicit when-to-use statement and no routing guidance relative to analyze_discovery_readiness or build_visibility_action_plan.

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