Retrieve saved project decisions and context from a local SQLite store using keyword and full-text search. Look up past notes to inform new work.
Search memories with lexical/FTS retrieval.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| project_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds one genuinely useful behavioral fact — retrieval is lexical/FTS, i.e. keyword matching rather than semantic similarity — but says nothing about ranking, result count defaults, or project scoping.
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 zero filler, which is efficient and easy to parse. It is arguably too terse for its job, but the brevity itself is not the problem.
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?
An output schema exists, so return values need not be explained. However, for a 3-parameter search tool with 0% schema coverage, the description omits pagination/limit semantics and project scoping, leaving the agent to guess how to narrow results.
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% for 3 parameters, so the description must compensate and largely does not. The 'lexical/FTS' phrase hints that the query string is a keyword expression rather than natural language, but limit (default 10) and project_id (nullable scoping filter) are entirely undocumented in both the schema and the description.
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), resource (memories), and retrieval method (lexical/FTS), so the agent knows this is keyword search rather than semantic lookup. It does not, however, distinguish itself from sibling memory_recent or explain how it differs from memory_get, so it stops short of full sibling differentiation.
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, no statement of prerequisites, and no reference to alternatives such as memory_recent or memory_get. The agent must infer from the name alone that this is the keyword-search path versus those siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.