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

Annotations already declare read-only, idempotent, closed-world, and the description adds the behavior that matters beyond that: no live assistant is queried, a missing business yields 0 rather than an error, and a name matching several businesses returns them instead of a score. These are non-obvious return-shape behaviors an agent could not derive from 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, front-loaded with the core operation and then the metric breakdown, the read-only constraint, and edge cases. Dense but each clause carries information; only the parenthetical assistant enumeration is slightly heavy.

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 describe the return values, and it does: score out of 100, 95% interval, prior edition, per-assistant score, and most-named names. Combined with the two alternative return shapes (0, or a list of matches), an agent knows what to expect from every call.

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 100%, so baseline is 3, but the description adds a real matching rule: 'Category and place are matched as ai_index_lookup matches them', which constrains how loose the input strings may be. The language parameter is left to the schema, which is acceptable given full 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?

States a specific verb and resource ('Reads the AIGROW Score of one business on an AI Visibility Index page') and immediately defines what the score measures: the share of assistant answers naming the business, out of 100. The clause 'no website is read and no assistant is asked' implicitly separates it from live-check siblings like check_ai_visibility.

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?

Edge cases are spelled out: an unlisted business reads 0 and an ambiguous name returns the candidate businesses instead of a score. It also says the tool only reads published counts, which tells an agent this is the cheap, non-live path. It never names check_ai_visibility as the alternative for live measurement, so the when-to-use routing is inferred rather than stated.

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