Search saved coding memory entries by keyword with an optional type filter to retrieve gotchas, decisions, or patterns.
AMP: search entries by keyword. Optional type filter.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | ||
| query | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden, yet it discloses nothing beyond 'search': not what a match covers (title, body, tags), whether results are ranked or capped, case sensitivity, or whether full entry bodies are returned. For a tool with zero annotation coverage this is a substantial gap.
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?
Two short front-loaded sentences with no padding, and the core purpose leads. The terseness comes at the cost of substance rather than being padded, so it is efficient but slightly under-specified.
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?
With no annotations, no output schema, and 0% schema description coverage, the description should compensate with match semantics, result limits, and the meaning of the type enum — none of which are present. The tool is simple, but what an agent needs to call it well is still missing.
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 0%, and the description only restates the parameter surface: 'keyword' maps to query and 'optional type filter' maps to the type enum. It adds that type is optional, but never explains what the seven enum values (gotcha, decision, attempt, note, detection, pattern, preference) mean or what text query matches against.
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 (entries) qualified by 'by keyword', so an agent knows this is a keyword lookup rather than a direct fetch. It never distinguishes itself from amp_read or amp_resume, so the sibling differentiation needed for a 5 is absent.
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 only usage hint is that the type filter is optional; there is no statement of when to search versus using amp_read/amp_resume, no prerequisite or scope conditions, and no exclusions. An agent must infer the routing decision entirely on its own.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.