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

Goes well beyond the annotations: result ordering (closest to furthest match), inclusion of canonical page URLs, exclusion of deprecated and unlisted places, drafts surfaced with status 'draft', graceful fallback to name/text search under budget exhaustion, and the exact error shape for an out-of-vocabulary tag. That is a lot of behavior an agent could not otherwise predict.

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-loads the core purpose and examples, then layers filtering, result shape, freshness rules, fallback, and error behavior in a tight sequence. Six sentences and each one carries distinct, non-redundant information.

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 still covers the return format (ordered results with canonical URLs), inclusion rules, degraded-mode behavior, and the error contract. An agent has everything needed to call this correctly and interpret the failure case.

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 already 100%, so the baseline is 3, but the description adds genuine meaning: tags are AND-matched ('every tag must match'), and an invalid tag yields { "error": "invalid_input" }. It also points at list_tags and list_categories for vocabulary, which the schema only hints at for tags.

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 (searches), resource (locally owned places), geographic scope (Milwaukee County), and mode (by meaning), backed by two concrete query examples. This differentiates it clearly from sibling tools like get_place, places_near, and search_records.

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?

The examples ('friday fish fry with perch', 'frozen custard on the south side') make the intended semantic-search usage clear, and the description explains the degradation path when the embedding budget is exhausted. It stops short of explicitly naming when to prefer places_near or plain search over this tool, so the choice is inferable rather than stated.

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