search_treks

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

With no annotations, the description carries the full burden and does so well: it discloses filter behavior, units, default radius, and the use of Nominatim for geocoding. It omits return format and error behavior, but an output schema exists to cover some of that.

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 organized paragraph, front-loaded with the purpose and then a structured enumeration of filters. It is efficient with no wasted words, though bullet points could improve scannability.

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 tool with 12 parameters and no annotations, the description covers most filters but leaves `limit` and `query_text` unexplained, and lacks details on search result ordering or pagination. The output schema helps, but the overall guidance feels slightly incomplete for full agent decision-making.

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 description adds significant meaning for 10 of 12 parameters, explaining units, filter semantics, and naming sources. It does not explain `limit` or `query_text`, which remain ambiguous gaps despite the schema.

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 clearly states the tool's purpose: 'Recherche des treks' (search treks) on the GeoTrek instance. It distinguishes itself from sibling list tools by focusing on searching with filters rather than listing available values.

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 provides context on how to use filters, notably referencing list_labels and list_activities for valid names, and explains the two geographic proximity options. It does not explicitly contrast with alternatives, but the intent is clear given the sibling tools are list tools.

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