Report whether a stored memory was useful, not useful, incorrect, or outdated to help assess and improve local memory quality.
Report whether a memory was useful, not useful, incorrect, or outdated. No task ID needed. Feedback is an append-only assessment, not automatic verification or permission to modify the memory. Submit once per assessment; retries add reports.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | ||
| verdict | Yes | ||
| memory_id | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds meaningful context beyond annotations: "append-only" indicates the report accumulates rather than overwrites, and "Submit once per assessment; retries add reports" discloses the non-idempotent behavior and warns against retrying. This reinforces the idempotentHint=false annotation with concrete operational meaning.
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?
Four short sentences, each earning its place: purpose, no task ID needed, append-only clarification, and the one-report-per-assessment warning. Front-loaded and free of 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?
For a non-mutating assessment tool with three simple parameters and no output schema, the description is sufficient: it defines the verdict space, clarifies the append-only nature, and warns against retry. Missing only an explicit statement of what happens to the memory after feedback, but the append-only note covers the essential behavior.
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%, so the description must carry the load, but it only partially compensates. It describes the verdict semantics implicitly (the four categories) but never explains what memory_id refers to beyond its name, or what the optional reason field is for. Baseline 3 is appropriate given the top-level description covers the verdict but leaves other params thin.
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+resource (report feedback on a memory) and enumerates the exact verdict values, which differentiates it from siblings like memory_add or memory_archive that mutate memory state. The "not automatic verification or permission to modify the memory" clause sharpens the boundary.
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?
Clarifies that no task ID is needed and that feedback is an append-only assessment rather than a modification or verification action, which routes the agent away from mutation tools. It does not explicitly name alternative tools to use for correcting or archiving a memory, so it falls just short of 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.