Search stored memories by keyword before answering questions about users, projects, or prior discussions; if nothing matches, say you do not know instead of guessing.
Search memories by keyword. Call this BEFORE answering anything about the user, their projects, or things that may have been discussed before. If nothing is found, say you do not know — do not make it up.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Keywords or a question | |
| category | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it correctly conveys that this is a read/search and what to do on empty results. It says nothing about result volume, ranking, pagination, or whether the search is exact-match vs semantic — behaviors an agent would want to know before trusting a negative result.
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?
Three short sentences, front-loaded with the action and immediately followed by the triggering condition. Every sentence earns its place; no restatement of the name or filler.
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, yet the description never indicates what a hit looks like (snippet, score, metadata) or how results are ordered and capped. The mandatory pre-answer usage is well covered, but an agent still lacks enough detail to interpret or size the response.
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 33%, and only `query` is documented ('Keywords or a question'). The description adds no meaning for `limit` (no default or max mentioned, despite the 1-50 range) or `category` (the seven-value enum is self-labeling but its filtering semantics are unstated). With low coverage the description should compensate and does not.
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 and resource ('Search memories by keyword'), which is clearly readable as a retrieval operation distinct from save/get/delete siblings. It does not explicitly contrast itself with memory_context, memory_get, or memory_list, so sibling differentiation is left to inference.
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?
Strong prescriptive guidance: call it before answering anything about the user, projects, or prior discussion, plus an explicit fallback ('if nothing is found, say you do not know'). It gives no exclusions and never names the alternative siblings that would cover a narrower or broader case.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.