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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It transparently exposes the coverage limitation (OSM relation 147488 and the specific out-of-coverage cities) and the list_categories prerequisite. It does not, however, disclose how the filters combine (AND vs OR) or what fields the returned result contains, which would aid the agent further.

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?

Two sentences deliver the purpose, the key prerequisite, and a precise coverage boundary. The text is front-loaded: the action and resource appear first, and every clause contributes either a functional description or a constraint. No fluff or repetition.

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 5 parameters and no output schema, the description needs to clarify both the mapping of the 'city' mode and the shape of results (e.g., place names, IDs, ordering). It provides the crucial scope rule and the category prerequisite, but the indeterminate city filter and the absent result description leave enough ambiguity that it is not fully complete.

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?

Schemas already describe 100% of the parameters, so the description needs only to add clarifications. Instead, it introduces a 'city' search mode that does not map to any property in the schema, requiring the agent to guess whether 'city' is represented by `q`, `category`, or an undeclared parameter. This ambiguity makes the description misleading rather than informative.

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 specific verb and resource — 'Find places' in Metro Manila — and enumerates the search dimensions (city, category, name fragment, near a coordinate). The explicit geographic scoping immediately distinguishes it from the sibling tools like get_place or list_categories.

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 description gives an explicit prerequisite: 'Call list_categories before filtering on a category.' It also flags the geographic coverage boundary ('no Cebu, Davao, Baguio, or Dumaguete'), telling the agent when not to rely on this tool. It doesn't name alternative tools for those other regions, so it stops short of a perfect 5.

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