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

Beyond the annotations (readOnly/idempotent/non-destructive), the description discloses the exact ranking algorithm and tie-breakers, the 0.5 km distance banding, the guarantee that subscription tier never affects order, and that attributes are owner declarations rather than verified facts. This is behavioral context an agent could not get from the structured fields, and it does not contradict the readOnly annotation.

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?

Purpose and ranking are front-loaded in the first sentence, followed by important caveats and then the return shape — a logical order. The prose is dense and information-rich, though the 'owner declarations, not verified facts' point marginally duplicates the `dietary` schema text and the sentences run long.

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, but the description explicitly lists the returned fields (slug, name, city, distance_km, is_open_now, channels, declared attributes, freshness, menu URL) and states that results are paginated. Combined with the ranking and exclusion rules, an agent has everything needed to call and interpret this tool correctly.

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 67%, and the description compensates for the gaps: it explains the effect of `near` and `radius_km` banding, the exclusion behavior tied to filters, the interaction between `open_now` and unknown hours, and the timezone basis of is_open_now. It adds meaning beyond the schema for the ambiguous parameters even though a few fields (q, city, page/limit) get no extra prose.

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 opens with a specific verb+resource+scope ('Search the public directory (opt-in venues only)') and enumerates every filterable dimension, which cleanly separates it from siblings like get_restaurant and list_public_menus without needing to open any schema.

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 rich conditional guidance — venues without a declaration are excluded only when an attribute filter is used, venues without coordinates only when `near` is set — so the agent understands the consequences of each filter. However it never names an alternative tool or states when to prefer get_restaurant over this search, so it stops short of full sibling routing.

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