Search durable memory across sessions by query, optionally filtered by domain, to retrieve standing rules, current state, open loops, or historical facts with more results than a direct read.
Broader sweep with the same ranking as read_memory (more results).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| domain | 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?
With no annotations, the description carries the full burden and delivers little: it discloses that ranking matches read_memory and returns more results, but says nothing about pagination, result caps, ordering guarantees, or whether the memory store is read-only. The one comparative fact is genuinely useful, but the behavioral picture is thin.
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 short sentence with no filler, and the differentiating comparison is front-loaded. It is efficient; the brevity is partly a virtue and partly the source of the gaps scored elsewhere.
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, but for a three-parameter search tool with zero schema descriptions and no annotations the definition leaves the agent guessing about parameters and scope. It is not complete enough to invoke confidently.
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% across three parameters (query, limit, domain), so the description must compensate and largely does not. 'More results' weakly gestures at the limit parameter, but query and domain—including what a domain scopes to—are completely unexplained anywhere.
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 positions the tool relative to a sibling ('broader sweep... same ranking as read_memory') and hints at result volume, but never states the verb+resource plainly (e.g., 'search stored memories by query'). An agent must infer the purpose from the name and the read_memory comparison rather than reading it.
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 phrase 'broader sweep ... (more results)' implies this is the wider-coverage alternative to read_memory, which is a usable selection hint. However, it never states an explicit when-to-use/when-not condition, prerequisites, or how broad the sweep actually is.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.