Skip to main content
Glama

failures

Read-onlyIdempotent

Retrieve known agent failure modes for a file, task or error text, each paired with the guard that stops it, so coding agents can avoid repeating diagnosed mistakes.

Instructions

Mistakes agents made with a file (for) or with an error text (match), each with the guard that stops it. The whole ledger is not offered: scope it with for, match or one shape's id. Successful structured results include the command record and exit code.

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": "failures"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoa key of atlas.yaml/agent_failure_modes
forNoa file or task: only the shapes most relevant to it, with their tells
limitNohow many shapes --for returns
matchNoan error text: the shapes whose declared signature it matches (exit 1 when none does)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds a genuinely non-obvious behavioral trait: there is no full-listing mode and an unscoped call will not return everything. It also hints at the result payload (command record and exit code), though vaguely.

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 compact sentences with the scoping constraint front-loaded and no filler. The phrasing is compressed to the point of opacity in places, particularly 'Successful structured results include the command record and exit code,' which costs clarity without adding much.

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?

There is no output schema, so the description bears the burden of explaining what comes back, and it only gestures at this ('each with the guard that stops it', 'command record and exit code'). For a four-parameter lookup tool the invocation side is adequately covered, but the return shape and the interaction between `for` and `limit` remain thin.

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 100%, so the schema already documents all four parameters, and the description largely restates them (`for` = file or task, `match` = error text, `id` = one shape's key). It adds the useful nuance that exactly one scoping mode should be chosen and that `for` returns ranked shapes with their tells, but that is marginal over the schema descriptions.

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 names the resource precisely: recorded agent mistakes tied to a file or an error text, each paired with the guard that prevents it. The verb is implicit (a retrieval of the failure ledger), and the closing sentence about 'successful structured results' is ambiguous enough that an agent could mistake it for a reference to the `successes` sibling rather than to the tool's own return payload.

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?

It gives an explicit, actionable constraint: the whole ledger is not offered, so you must scope with `for`, `match`, or a shape `id`. That is real when-to-use guidance. It stops short of routing the agent away from alternatives such as `successes` or `proof`, so no exclusions are stated.

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