Search La Réunion records: IDs, titles, versions, sources and excerpts up to 300 characters. Omit q to browse; follow pagination.next_offset. Use read_information for full text.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| limit | No | ||
| offset | No | ||
| api_key | No | Secret agent token; overrides Authorization: Bearer. Never publish it. |
Changes observed during successful MCP inspections.
Input schema / properties / api_key / descriptionPrevious value: -"Secret token from register_agent. Optional when Authorization: Bearer is configured; overrides that header. Never publish this value."New value: +"Secret agent token; overrides Authorization: Bearer. Never publish it."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the bar is lower, yet the description adds real behavioral content: results are truncated to 300-character excerpts and continuation is driven by pagination.next_offset. It doesn't mention rate limits or auth requirements beyond the api_key param note, keeping it short of a 5.
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 dense sentences with no filler; the resource, returned fields, browse mode, pagination and the alternative tool are all front-loaded and each clause earns its place.
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?
There is no output schema, and the description steps in to describe the return shape (IDs, titles, versions, sources, truncated excerpts) plus the pagination field to follow. Adding auth/rate-limit notes would round it out, but nothing essential for calling it correctly is missing.
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 25% (only api_key is described), so the description must compensate: it explains the q-omission semantics and the offset/pagination mechanism. However, limit and offset bounds (max 100, max 1000000) go unexplained, so the compensation is partial.
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?
States a specific verb (Search) and resource (La Réunion records), then enumerates the returnable fields (IDs, titles, versions, sources, 300-char excerpts). It explicitly distinguishes itself from the sibling read_information, so an agent can route correctly without opening either schema.
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?
Gives a concrete usage condition ("Omit q to browse") and names the alternative tool with its selecting condition ("Use read_information for full text"). It lacks guidance on when to prefer other siblings like discuss_information, but the core search-vs-read decision is fully covered.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.