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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial behaviour beyond them: default scope when place or time is omitted (all Greater San Diego, next seven days), multi-page results signalled by next_offset, and the licensing constraint that listings carry a localhum link for personal, non-commercial use. Return contents are listed rather than left to the output schema, which is mild duplication, and rate-limit/error behaviour is not addressed.

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 purpose and usage, then defaults, then return shape and licensing — a sensible information hierarchy with no filler. The middle paragraph of quoted example questions runs slightly long, but each clause carries distinct guidance.

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 10-parameter tool whose schema is fully documented and which has both annotations and an output schema, the description still covers the gaps that matter: default search scope, out-of-region behaviour, pagination via next_offset, and licensing terms. Nothing an agent needs in order to call it correctly is missing.

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 genuine semantics: the question must be passed verbatim with place and time intact rather than rewritten into keyword lists, and place/time/kinds/exclusions/free/for-kids are all read out of the words, which clarifies the interaction between the required question and the optional override parameters. It stops short of explaining precedence per-parameter, which the schema does handle individually.

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?

"Find what's on at San Diego's bars, breweries, clubs, cafes, galleries and small venues from a question in plain words" gives a specific verb, resource and geography. The scope statement ("covers San Diego County only") plus the pointer to localhum_areas and away from localhum_venue makes it clearly distinguishable from both 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?

Explicit when-to-use ("questions about events or things to do in San Diego") with an enumerated set of intents, plus explicit when-not (outside San Diego County → says so and lists nothing). It also describes how to split multiple wishes into separate calls and names localhum_areas for neighbourhood resolution.

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