Skip to main content
Glama

remember_for_project

Store one dated, signed, project-specific lesson in shared project memory so every session can read it; send cross-project rules to the orchestrator instead.

Instructions

Keep one thing you learned about this project (for example "tests need the dev database running") in its memory, dated and signed; every session on the project reads it. A rule worth keeping for every project goes to the orchestrator instead (an FYI); only it adds to the shared memory.

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": {
      "line": "<line>"
    },
    "name": "remember_for_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
lineYes
projectNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.57.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does meaningful work: it discloses that entries are dated and signed automatically, that one item per call is expected, and that every session on the project reads the entry (persistence and audience). It does not mention permissions, duplicate handling, or failure behavior, which keeps it below a 5.

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?

Three dense clauses with the core action and scope front-loaded, plus the concrete example in parentheses that makes the granularity concrete. Slightly winding sentence structure but no padding.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and the description covers scope, persistence, and routing. However, for a two-parameter write tool with zero annotation and zero schema-description coverage, the unexplained 'project' parameter and absent permission or duplicate-handling context leave real gaps.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must define both parameters, but it only implicitly maps 'one thing you learned' to the required 'line'. The optional 'project' parameter and its empty-string default are never addressed, leaving an agent unsure whether omitting it targets the current project.

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?

States a specific verb (keep/remember) and a specific resource (this project's memory), with the key qualifier that it stores exactly 'one thing you learned'. It also draws a boundary against the global/orchestrator route, though it never names the sibling tool that performs that route.

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?

Gives a clear when-to-use (a project-scoped lesson, illustrated with a concrete example) and an explicit when-not-to-use (a rule that applies to every project belongs to the orchestrator). The only weakness is that the alternative is described rather than named, so an agent must infer the sibling from its function.

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