kernel_places_near

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

With no annotations present, the description carries the full burden, and it does disclose meaningful behavior: results are nearest-first, distances are in km, and inclusion depends on coordinates coming from a map link, manual entry, or geocoding. It also flags that 'any address' only works when the geocoder is on, which is a real operational constraint. It does not cover permissions, rate limits, or what happens with items lacking coordinates beyond pointing to another tool.

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 core behavior and the `where` formats are front-loaded in the first sentence, and the second sentence adds only the coordinate-inclusion rule and the alternative tool. The parenthetical about the geocoder is dense but earns its place. Slight verbosity in the enumeration of coordinate sources.

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?

An output schema exists, so return values need not be described, and the description covers ordering, units, and inclusion rules for a six-parameter proximity search. The main remaining gap is the meaning of the `kinds` values (especially 'manual') and how `limit` interacts with ordering, which an agent could plausibly get wrong.

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 only 33%, so the description must compensate, and it does well for the required `where` parameter by listing accepted formats (coordinates, map link, known place name or address). It adds nothing for `kinds`, `limit`, or `radius_km` beyond the word 'radius' and 'within a radius'; the enum values including 'manual' are enumerated in the schema but never explained. Partial compensation for the coverage gap lands at 3.

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 query shape: 'What is near a place: events, trips, hotels and travel activities within a radius, nearest first, with the distance in km.' It names the item types returned, the ordering, and the distance unit, which separates it from a general place search. It stops short of contrasting itself directly with the sibling kernel_places_search, so it is clear but not fully differentiated.

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 states one important precondition — items only count once they have coordinates — and routes the agent to kernel_places_list with missing=true for everything else. That is genuine routing guidance, but there is no explicit statement of when to prefer this over kernel_places_search or which radius/kind combinations make sense.

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