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

Annotations only declare readOnly/idempotent/non-destructive/openWorld=false; the description goes well beyond that. It discloses the 25-result cap, that ordering and gaps explain truncation, that website/OSM facts are unconfirmed with source and date, that posted hours do not establish open-now, that a directory match does not confirm stock or slots, that virtual results have null distance and no directions, and that research_errand URLs share a two-page limit. This is exactly the behavioral context an agent needs to avoid over-claiming.

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 is front-loaded in the first clause and the caveats that matter (unconfirmed facts, posted hours vs open-now, virtual results) each earn their place. The long comma-separated enumeration of return fields is dense and hard to scan, but since there is no output schema those field names carry real informational value, so it is defensible even if not tidy.

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 rightly enumerates the returned fields and their caveats, covers edge cases (virtual results, missing data_coverage), and points at follow-up flows. The remaining gap is parameter-side: radius_m and q behavior are unaddressed, which matters for a 7-parameter search tool with 0% schema description coverage.

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 description coverage is 0%, so the description must compensate for seven parameters. It maps category, coordinates, and optional city to prose, and gives a meaningful constraint on research_fact_types (request only relevant ones), but it never mentions q or radius_m and does not explain any of the ~56 enum values. Partial compensation only.

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: a free, no-sign-in directory search by category, coordinates, optional city, returning nearby businesses. Clear to an agent what it does. However, it never names or distinguishes itself from close siblings such as discover_local, search_local_offerings, or find_business, so an agent must guess which of the several find/discover/search tools is correct.

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?

Usage is implied rather than stated: 'free directory search with no sign-in' and 'request only relevant research_fact_types' give partial conditions, and the note about preserving wider_search/contact next steps hints at follow-up flows. But there is no explicit when-to-use versus alternatives, no mention of discover_local or search_local_offerings, and no statement of what this tool cannot do that a sibling can.

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