Memory MCP

gotcha

Flag surprising codebase behavior to store durable insights for future sessions. One observation per call, with related knowledge returned.

Instructions

When something surprises you or doesn't work as expected, flag it here. Example: {"lobe": "my-project", "observation": "Gradle cache must be cleaned after Tuist changes or builds silently use stale artifacts"} Store facts that help future sessions, not notes about this one. Wrong: "Build failed because of stale cache." Right: "Gradle cache must be cleaned after Tuist changes." One insight per call. Persists across sessions, gets priority in brief() and recall(). Returns related knowledge. Required params: "lobe", "observation".

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": {
      "lobe": "<lobe>",
      "observation": "<observation>"
    },
    "name": "gotcha"
  }
}

Input Schema

Name	Required	Description	Default
`lobe`	Yes	Memory lobe name. No lobes configured yet — run memory_bootstrap(lobe: "your-project", root: "/absolute/path/to/repo") first.
`observation`	Yes	The gotcha. Write naturally — first sentence becomes the title.
`durabilityDecision`	No	Use "store-anyway" only when re-storing after a review-required response.	default

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Aug 10, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses persistence across sessions, priority in brief()/recall(), and that it returns related knowledge. It also enforces 'One insight per call.' This is solid behavioral disclosure, but it doesn't mention potential side effects like duplication or error conditions, which would push it higher.

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

Conciseness5/5

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

The description is appropriately sized and well-structured. It starts with the core purpose, then gives an example, then clarifies the distinction between facts and notes, then states constraints and behavior. Every sentence adds value, and the structure supports quick scanning.

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

Completeness5/5

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

For a simple write operation with a rich schema and no output schema, the description is complete. It covers purpose, when to use, how to phrase observations, persistence, return behavior, and required parameters. The only optional parameter (durabilityDecision) is fully explained in the schema, so no additional description is needed.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description adds value beyond schema by providing a full example of lobe and observation, and by giving wrong/right examples for how to phrase the observation. It also explicitly flags the required params, making parameter usage clearer.

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

Purpose5/5

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

The description clearly states the tool flags surprising or unexpected issues as 'gotchas' for future sessions. It provides a concrete example and distinguishes itself from siblings like learn, prefer, and conventions by emphasizing the specific use case. The verb+resource combination is specific and unambiguous.

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

Usage Guidelines4/5

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

The description explicitly says when to use: 'When something surprises you or doesn't work as expected.' It also gives right/wrong phrasing examples and advises 'Store facts that help future sessions, not notes about this one,' which is a clear guideline. However, it doesn't explicitly name alternatives or exclusion cases, leaving some room for interpretation.

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

Deploy Server