Skip to main content
Glama

Say how a search went

memory_feedback
Idempotent

Tell memory how one of its searches went, by the search_id that search returned: wrong when what came back was wrong, missing when the answer was not in it, ok when it served. Use it when the person says an answer from memory was wrong or incomplete, or when you found the answer somewhere else; put what was true in note. Memory keeps the note as something the person said, and answers such questions better afterwards.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "search_id": "<search_id>",
      "verdict": "<verdict>"
    },
    "name": "memory_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoWhat was true, or what was missing: kept as a note memory reads.
verdictYes
search_idYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a write (readOnlyHint=false), idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds the consequence of the call: the note is retained as 'something the person said' and improves later answers, which is genuine behavioral information not present in any structured field. It stops short of saying what happens to an unknown or repeated `search_id`, which the idempotent hint only partially covers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first clause, and the colon-delimited verdict list is easy to scan. The final sentence about notes being retained earns its place because it conveys effect. A few clauses are chained with commas, making it denser than necessary, but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter, non-destructive write tool with no output schema, the description covers purpose, triggers, each verdict, note content, and downstream effect. The remaining gap is edge-case behavior (invalid search_id, repeated submissions beyond the idempotency hint), which is minor and partly covered by annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, so the description carries real weight, and it does define all three verdict values in plain language rather than restating the enum. It also explains what belongs in `note` ('put what was true') and where `search_id` comes from. However, it adds little about the length limits or nullability of `note`, or the format of `search_id` beyond its origin.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Tell memory how one of its searches went') and ties it to the `search_id` that a search returned, which cleanly separates it from the search tools themselves. It does not name a sibling outright, so an agent must infer the pairing from context rather than read it, keeping it just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit trigger conditions: 'when the person says an answer from memory was wrong or incomplete, or when you found the answer somewhere else.' The three verdicts are defined in behavioral terms (`wrong` = what came back was wrong, `missing` = the answer was not in it, `ok` = it served), so the agent knows exactly which condition maps to which argument.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources