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

Annotations only declare readOnly/idempotent/non-destructive, and the description adds substantial non-obvious behavior: null-score preconditions, integer rounding that can turn a positive share into 0, note-bounded forms, sample-size and Wilson-interval semantics, early-reading thresholds, thinBasis fragility, and modelVersion non-comparability. It also defines the statistical-tie rule and the interval rounding pitfall. This is well beyond what the annotations convey.

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 purpose is front-loaded in the first sentence, but the body is a dense, run-on sequence of caveats covering rounding, sampling, intervals, ties, and versioning. Much of it is genuinely useful for interpreting output, yet the volume and lack of structural breaks (no lists, heavy clause chaining) make it harder to scan than it needs to be.

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?

There is no output schema, so the description must carry the full burden of explaining return values, and it does: score, scoreBasis, thinBasis, modelVersion, shareOfVoicePct, shareOfVoiceSample (n, questions, interval, tooThin, earlyReading), and rivals with versusYou/rivalsBasis. It also covers edge cases like null rank and name-only competitors, making it complete for a complex scoring tool.

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?

With schema description coverage at 100% and a single optional siteId fully documented in the schema, the baseline of 3 applies. The description adds no further meaning to siteId beyond what the schema already states about select_site and API-key requirements.

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 opening sentence gives a specific verb and resource ('Get a site's AI Visibility Score (0–100 + letter grade) and competitive rank') and defines the concept in one phrase ('how findable the site is across AI search engines'). It also explicitly separates itself from a sibling: 'the site audit alone is readiness (get_geo_audit), not visibility,' so an agent can tell the two apart without opening either schema.

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?

It clearly routes the agent away from get_geo_audit and states the precondition for a non-null score ('until at least one unbranded (discovery) question has been measured') plus when rivals is empty. It also frames what the tool answers ('who is ahead?'). It stops short of a full use-when/use-when-not matrix against every sibling, but the alternative and conditions are explicit.

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