Search stored reasoning chains by goal similarity to recover relevant past solutions for a project, filtering by similarity threshold.
Search stored reasoning chains by goal similarity (FTS5 + Jaccard).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max rows (default 5). | |
| query | Yes | Goal-like query text. | |
| project | No | Project name/path (default: active). | |
| threshold | No | Minimum Jaccard similarity (default 0.3). |
Changes observed during successful MCP inspections.
v4.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and closed-world, so the safety profile is covered. The description adds the useful detail that matching is similarity-based (FTS5 + Jaccard), hinting at ranked, non-exact results, but says nothing about result format or scoring output since no output schema exists.
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?
A single front-loaded sentence with no filler; every clause (what is searched, how it is ranked) 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?
For a read-only search tool with fully documented params and annotations covering safety, this is adequate, but the absence of any return-shape or ranking-output explanation (no output schema exists) leaves a gap an agent might need.
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 all four parameters (query, limit, project, threshold) are already documented in the schema, making 3 the baseline. The description adds only the ranking mechanism, not extra parameter semantics.
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 (stored reasoning chains), plus the matching mechanism (FTS5 + Jaccard). It is distinguishable from generic siblings like search_codebase or memory_search by naming 'reasoning chains', but it does not explicitly contrast with reasoning_list or reasoning_save.
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?
There is no when-to-use guidance. The phrase 'by goal similarity' implies the query should be goal-like, but the description never says when to prefer this over siblings like reasoning_list or memory_search, nor any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.