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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description still adds substantial behavior: computed fields (nextSpanishMass/nextEnglishMass on America/New_York clock, inSeasonNow), the offEastEnd referral flag, an editorial policy of quoting provider language rather than asserting safety, a cap of 8 results, and the townScope.recognized:false → empty rows + didYouMean path.

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 what the directory contains, then record shape, then computed fields, then query mechanics, then the empty-result path — a sensible order. It is a single dense paragraph, though, and the field-policy and townScope material would scan better as separate sentences or fragments.

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?

All three optional parameters are accounted for, no-argument behavior is defined, the 8-row cap is stated, and the failure mode of an unrecognized town is fully described. With no output schema present, the description carries the record shape (`phone`, `source`, `lastVerified`, bilingual `description`) and does so adequately.

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 the baseline is 3, but the description adds meaning the schema doesn't: 'query' accepts either language and free-form phrasing, 'need' is a shortcut vocabulary rather than a filter, and the town argument is fuzzy-matched with recognition feedback and near-match suggestions when it fails. That last point materially changes how an agent should supply and recover from the town parameter.

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 description names a specific resource (the guide's bilingual community directory of free and low-cost services) and enumerates the domains it covers — legal aid, food, shelter, classes, worship, soccer. An agent can tell instantly this is the social-services directory call, distinct from siblings like search_places or urgent_care.

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 gives clear operating context: 'query' for a free-form need in either language, 'need' as a shortcut vocabulary, 'town' for a hamlet or region, and explicit no-argument behavior (lists needs and towns covered). It stops short of naming when to prefer a sibling tool such as urgent_care for a medical question, so no exclusion guidance is present.

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