Skip to main content
Glama

cachly — Explain it once. Every AI knows it.

team_learn

Store a lesson in a shared team brain so all team members benefit. Like learn_from_attempts, but REQUIRES an author name for attribution. Shows up in team_recall with "by " so the team knows who learned it.

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": {
      "author": "<author>",
      "topic": "<topic>",
      "outcome": "<outcome>",
      "what_worked": "<what_worked>"
    },
    "name": "team_learn"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoTags for categorization
topicYesTopic in category:keyword format (e.g. "deploy:api")
authorYesYour name or handle (required for team attribution)
outcomeYesWhat happened
commandsNoCommands that worked
severityNoImpact level
file_pathsNoRelevant file paths
instance_idNoUUID of the shared team brain instance
what_failedNoWhat did NOT work (avoid this)
what_workedYesWhat worked (the solution)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations supplied, the description carries the burden, and it does disclose a real behavioral trait: the entry surfaces in team_recall rendered as "by <author>", which tells the agent the write is team-visible and attributed. It is silent on permissions needed to write to a shared brain, what happens on duplicate topics (overwrite vs. append), and how instance_id affects targeting, which matters for a 10-parameter mutation.

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 short sentences, front-loaded with the purpose, then the sibling contrast, then the downstream visibility consequence. The parenthetical "by <author>" formatting detail earns its space; there is no filler.

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?

Given ten parameters, four required, no annotations, and no output schema, the definition covers the essentials (purpose, attribution requirement, team visibility) but leaves gaps around duplicate handling, instance_id semantics, and failure behavior. Adequate to invoke correctly in the happy path, not complete for edge cases.

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 description coverage is 100%, so all ten parameters including the topic format, enums, and required author are already documented in the schema. The description only reinforces that author is mandatory for attribution, adding little meaning beyond the structured field, so the baseline 3 applies.

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?

States a concrete verb+resource ("Store a lesson in a shared team brain") and immediately differentiates it from the sibling learn_from_attempts by its mandatory author attribution. An agent can pick between the personal and team variants without opening either schema.

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 comparison to learn_from_attempts plus the explicit "REQUIRES an author name" condition conveys the selection rule: use this when the lesson belongs to the shared team brain and needs attribution. It stops short of an explicit exclusion (e.g., "use learn_from_attempts for private/session-only lessons"), so it is clear context rather than a full when/when-not statement.

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.