apple_maps_search

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so extensively. It discloses that Apple returns a bounded set (~25 places) with no pagination, that it may relocate the search to a default region when nothing matches (reported by relocated=true), that sort and filters each cost a second upstream search, and that the response's filters block lists refinement chips. These are all significant behavioral traits beyond the basic 'search' action, making the tool highly transparent.

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?

The description is a single dense paragraph, but every sentence contributes useful information: core purpose, return fields, viewport limitation and workaround, fallback relocation behavior, and filter/sort mechanics. It is well-structured, leading with the core action and then layering details. It is a bit long but avoids redundancy and is acceptable for a complex search tool with many behavioral nuances.

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?

Without an output schema, the description must explain what the response contains, and it does: it enumerates fields per place (id, name, category, coordinates, formatted/structured address, phone, website, rating/review count, price level, weekly opening hours, hero photo). It also covers pagination absence, viewport adjustment, relocation behavior, and the filters/sort forwarding mechanism. This is a comprehensive and self-contained explanation for an agent to call the 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?

The input schema already has descriptions for all 9 parameters (100% coverage), so the baseline is 3. The description adds meaningful extra context: it explains that filters keys come from an unfiltered search's filters block, that sort and filters each incur an additional upstream search cost, and that the span default and range are relevant to viewport coverage. These additions go beyond the schema's per-parameter explanations, particularly clarifying usage of the filters and sort parameters.

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 'Search Apple Maps places near a coordinate', clearly stating the verb (search), resource (Apple Maps places), and scope (near a coordinate). It further elaborates the kinds of queries it supports (keyword, business name, category, street address) and differentiates the result places by noting they carry the apple place ID consumed by the place endpoint, implicitly distinguishing it from apple_maps_place and apple_maps_places.

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 provides clear context on when this tool is appropriate: it is the generic search for places near a coordinate, and it points to the place endpoint for a specific place ID. It also explains operational constraints like no pagination and the need to widen the span or move the center to cover more area. However, it does not explicitly name sibling search tools like apple_maps_autocomplete or apple_maps_category_search, nor does it state explicit exclusions for when not to use this tool.

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