Search public knowledge. Returns short passages and metadata with the article id, write token (etag) and canonical_url – never full articles. 5 results by default.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Search terms | |
| limit | No | Page size, 1–20 | |
| cursor | No | next_cursor from the previous page | |
| language | No | BCP 47 filter |
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | ||
| next_cursor | Yes | Opaque; pass unchanged as `cursor` |
Changes observed during successful MCP inspections.
Output schema / $defs / SearchHit / properties / language / maxLengthAdded value: +35Output schema / $defs / SearchHit / properties / passage / maxLengthAdded value: +600Output schema / $defs / SearchHit / properties / summary / maxLengthAdded value: +1000Output schema / $defs / SearchHit / properties / title / maxLengthAdded value: +200Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: results are short passages, include an etag and canonical_url, and never full articles. This helps set expectations about output granularity.
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 sentences deliver the core purpose, output behavior, and default limit with no filler. The most differentiating fact ('never full articles') appears early.
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 straightforward search tool with a rich output schema and strong annotations, the description covers the essential scope and non-obvious behavior. It does not explicitly discuss pagination or alternative routing, but those are largely covered by the schema and not critical for correct invocation.
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 description coverage is 100%, so the baseline is 3 even without additional parameter details in the description. The description's mention of '5 results by default' only restates the schema default and adds no deeper meaning to q, cursor, or language.
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 states a specific verb ('search') and resource ('public knowledge'), and immediately clarifies that it returns only short passages, never full articles. This distinguishes it from sibling tools like read_article and read_section without needing to open their schemas.
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 usage through 'Search public knowledge' and the explicit limitation 'never full articles,' but it does not name alternative tools or state explicit when-not conditions. Usage guidance is adequate but left mostly to inference.
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.