Search observation memories by query, project, topic, or type, with filters and truncated previews to quickly locate relevant stored knowledge.
Search observation memories with preview truncation and filters
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Filter by memory type | |
| limit | No | Max results (default 20, max 100) | |
| query | No | Search query | |
| topic | No | Alias for topic_key | |
| project | No | Filter by project name or ID | |
| topic_key | No | Filter by topic key |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the burden. "Preview truncation" is a genuinely useful disclosure that results are abbreviated previews rather than full records, but nothing is said about permissions, read-only vs. mutating behavior, pagination beyond the schema's limit, or result ordering.
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 waste. However, the brevity is close to under-specification rather than tight editing.
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 six-parameter search tool with no annotations and no output schema, the description should say how results are returned, what truncation means in practice, and how it relates to sibling search tools. Only the truncation hint partially addresses return shape.
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 100%, so all six parameters are already documented in structured data, and the baseline is 3. The description adds only the word "filters" — no semantics for query matching, topic vs. topic_key aliasing, or type values.
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 ("observation memories"), plus two scope traits (preview truncation, filters). It does not distinguish itself from sibling search tools like search_entries, search_by_tags, or vault_mem_timeline, which an agent would need in order to pick correctly.
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 statement of when to use this tool versus the many adjacent search/timeline/context siblings. No exclusions, no prerequisites, no scenario guidance — the agent must infer from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.