search_race_catalogSearch CourseProfiler's race catalog by race/course name and return direct CRSProf URLs that can be used as course sources.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum matches to return, default 5. | |
| query | Yes | Race or course name to search, e.g. Val d'Aran PDA. |
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query. | |
| matches | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavior itself. It clearly states the search action and the return of direct URLs, which implies a read-only operation. It goes beyond a tautology by explaining the result's utility. While it doesn't mention potential limits or rate limits, the core behavior is transparent enough for a search 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 description is a single, front-loaded sentence that efficiently captures the purpose, resource, and output. Every part contributes meaning, with no filler or redundancy.
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?
This is a simple search tool with a small input schema, a clear output schema, and no complex side effects. The description covers the essential purpose and the downstream use of the returned URLs. The presence of an output schema means the return structure is already documented, so the description does not need to elaborate further.
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 provides 100% coverage of both parameters: 'query' (the search term) and 'limit' (maximum matches). The description adds no further parameter details beyond what the schema already explains, so the baseline of 3 is appropriate.
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 verb 'Search' plus the resource 'CourseProfiler's race catalog', and specifies the output ('direct CRSProf URLs') and its purpose ('used as course sources'). This distinguishes it from all sibling tools, which are creation, validation, or import tools rather than search tools.
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 implies when to use the tool: when you need to look up a race/course by name and obtain its CRSProf URL for use as a course source. It gives clear context but does not explicitly state when not to use it or mention alternatives, though no direct alternative search tool exists among the siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct step in the course/race-planning workflow, and descriptions carefully separate concerns like importing, enriching, segmenting, and generating a plan. The main ambiguity is among the multiple get_*_requirements helpers, but their target phases are clear enough to avoid persistent misselection.
All tool names follow a consistent verb_noun snake_case pattern (create_, enrich_, export_, generate_, get_, import_, search_, submit_, validate_). There is no mixing of camelCase or inconsistent verb styles, making the API predictable and easy to navigate.
With 16 tools, the server is at the upper edge of the ideal range but each tool serves a distinct purpose in a complex pipeline covering course import, enrichment, segmentation, runner profiling, plan creation, PDF export, validation, and catalog submission. The count feels justified for the domain rather than bloated.
The toolset covers the full lifecycle from course discovery/import through enrichment, segmentation, runner profiling, race plan generation, PDF export, and catalog submission. Minor gaps exist, such as lack of artifact list/delete/update tools and no direct race-plan editing, but agents can work around these via get_artifact and get_job.