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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, non-open-world), so the bar is lower; the description adds real domain behavior beyond them, namely the coordinate/no-coordinate branching, the 'nobody is stationed yet' filter, and the economics warning that holding a place yields nothing directly. It omits pagination or sampling behavior beyond the limit param and says nothing about what fields a place record contains.

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?

Three sentences, front-loaded with scope, then the two modes, then the payout caveat — each sentence carries information. There is minor framing overhead in the opening clause about the site and the catalogue size, but it earns its place as scope context.

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 four-parameter, all-optional read tool with annotations and no output schema, the description covers the non-obvious parts: the two result shapes and the consequence of holding a place. Remaining gaps are minor — it never says what a returned place record looks like (name, id, coordinates) or how the 'sample' is chosen given the limit.

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% and the enum plus limit bounds are already documented, so the baseline is 3. The description does add meaning for lat/lng by explaining they restrict results to unoccupied places near that point, which the schema's bare 'Latitude'/'Longitude' does not convey. It adds nothing beyond the schema for limit or category.

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 states a concrete resource (a catalog of ~500,000 real places: churches, castles, houses, Daoist temples) and describes the two distinct operating modes based on whether coordinates are supplied. It does not explicitly name a sibling tool or contrast with one, but the sibling list contains nothing else about places, so disambiguation is not a live problem. The verb is somewhat implicit ('lists'), leaving the purpose clear but slightly indirect.

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 usable mode-selection guidance: supply lat/lng to get nearby places with nobody stationed, omit them to get a lit-count plus a sample. There is no statement of when not to use it, no mention of prerequisites, and no named alternative for related needs. Adequate but leaves the agent to infer the rest.

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