Run ranked hybrid searches across a local memory vault and return IDs, gists, and scores so you can fetch full text only for relevant nodes.
Ranked hybrid search across the whole vault. Returns ids + gists + scores (cheap) — an index, not the text. Pass the ids that matter to cairn_read for their full text — raise max_chars for very long nodes (cairn_fetch for a budgeted context pack).
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | ||
| query | Yes |
Changes observed during successful MCP inspections.
v0.3.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does reasonably well: it discloses the return shape (ids + gists + scores), explicitly flags that results are an index rather than full text, and signals relative cost ("cheap"). It doesn't mention any auth, rate limits, or ranking tunability, which keeps it below 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 sentences, both front-loaded with the highest-value facts (what it returns, how to continue). No filler, and every clause carries actionable information.
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 simple two-param tool with no output schema, the description adequately covers the return payload (ids/gists/scores), which is the main gap an output schema would otherwise fill. However, the absence of any guidance on `k` or query formulation leaves it only partially complete.
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 0% and the description explains neither parameter: `query` semantics (syntax, natural language vs keywords) and especially `k` (default 10, no stated meaning or cap) are undocumented. The only param-like mention, max_chars, belongs to a sibling tool, not this one.
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?
"Ranked hybrid search across the whole vault" gives a specific verb (search) and resource (vault) plus the retrieval strategy (hybrid ranking). It positions itself against cairn_read/cairn_fetch as a downstream step, though it doesn't clarify how it differs from search-adjacent siblings like cairn_wander or cairn_orient.
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 clearly describes the intended workflow (search here, then pass ids to cairn_read, or cairn_fetch for a budgeted pack), which is useful downstream routing. But there is no explicit "when not to use this" or comparison against the other lookup siblings (cairn_recent, cairn_wander, cairn_orient), so the choice among them is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.