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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavior: the data source (public page checks of sample sites), the quota cost of one trial use, and the fact that per-site records are not exposed. It does not state freshness or caching behavior for the month parameter.

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?

Front-loaded with the return contents, then the exclusion, then the parameter hint and quota note. Dense but every clause carries information; the single-block colon-list format is slightly harder to scan than separated sentences.

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?

With no output schema, the description does the work of describing the return payload in detail, which is the right call. The main remaining gap is include_definition, an undocumented flag whose effect an agent cannot predict from either schema or description.

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 75%, so the schema carries most parameter meaning. The description adds real value for category by tying it to list_reports' numbering and the empty-means-all default, but says nothing about month format, agent, or include_definition, leaving the least-documented parameter unexplained.

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?

States a specific verb and resource (industry-level GEO readiness aggregate) and enumerates exactly what is returned: 20-indicator averages, distribution, per-indicator fulfillment rate, AI bot allowance ratio, and the formula. It also explicitly excludes individual site data, which separates it from site-level siblings.

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?

Gives concrete usage context: category values come from list_reports' industry numbers, and leaving it empty means all industries. It also warns that the call consumes one unit of the trial quota, which shapes when an agent should spend it. It does not contrast against get_industry_brief or get_ai_insights, so the alternative-selection guidance is incomplete.

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