Skip to main content
Glama

body_lessons

Retrieve lessons learned from past failures for a specific tool or error code. Use them before retrying to avoid repeating known mistakes.

Instructions

What we already learned from failures - read it BEFORE repeating an attempt.

Every failed action leaves a proposed lesson (root cause + likely fix). These are the lessons that apply to a tool or an error code, newest first.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "body_lessons"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolNo
limitNo
error_codeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4/5.0
Behavior4/5

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

Without annotations, the description carries the burden well: it discloses provenance (every failed action leaves a proposed lesson), payload shape (root cause + likely fix), ordering (newest first), and read-only intent implied by 'read it'. It does not say what happens with zero matches, nor whether lessons are vetted versus merely 'proposed', which leaves a small ambiguity about trustworthiness.

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 purpose and the imperative call-to-action are front-loaded in the first clause, and the second sentence supplies exactly the context needed to interpret the results. No filler wording.

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?

Given no annotations, no output schema, and three loosely documented parameters, the description covers the essentials: what a lesson is, how results are ordered, and when to call it. The missing pieces are limit behavior and empty-result handling, which are minor for a small read-only lookup tool.

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 0%, so the description must compensate. It explains that lessons 'apply to a tool or an error code', which gives real meaning to the tool and error_code parameters, but the limit parameter and its default of 10 are never mentioned, and it is unclear whether both filters combine or either alone suffices.

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 the resource concretely: accumulated lessons from failed actions, each containing a root cause and a likely fix, filterable by tool or error code and ordered newest first. It is clearly distinct from every sibling (none of which deal with lessons), though the retrieval verb is only implied through 'read it BEFORE' and 'These are the lessons'.

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?

Explicit when-to-use guidance: 'read it BEFORE repeating an attempt', which tells the agent to consult this tool before retrying a failed action. There are no stated exclusions or named alternatives, but no sibling appears to overlap this function, so the routing risk is low.

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