Skip to main content
Glama

successes

Read-onlyIdempotent

Find recorded practices for recurring failures, with when to use them, evidence, and proving instruments; filter by file, task, or pattern ID.

Instructions

Look up recorded practices that address recurring failures, including when to use them, evidence and proving instruments. Scope by file or task with for, or by pattern id; limit applies to for. Use failures for the corresponding mistake patterns. 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": "successes"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoa key of atlas.yaml/agent_success_patterns
forNoa file or task: only the moves most relevant to it
limitNohow many moves --for returns

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety and repeatability need no restating. The description adds non-obvious context beyond that: what a successful result contains ('the command record and exit code') and the behavioral quirk that `limit` governs only the `for` path. It does not describe ordering, or what happens when neither `for` nor `id` is supplied, which is the remaining behavioral blind spot.

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, purpose front-loaded, followed by scoping and the sibling pointer — no filler or repetition. Slight denseness comes from stacked jargon ('moves', 'proving instruments') that costs a little parse time. It is appropriately sized for a three-optional-parameter lookup tool.

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?

With no output schema, the description usefully says successful results carry the command record and exit code, and it covers both scoping modes. But all three parameters are optional, and the description never states the default behavior — what is returned when neither `for` nor `id` is given — which is the main thing an agent needs before calling it bare. Otherwise adequate for a simple read tool whose annotations already carry the safety profile.

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 the baseline is 3, and the description earns a bump by adding cross-parameter meaning the schema only implies: `for` is a file-or-task scope, `id` is an alternative scope keyed on atlas.yaml/agent_success_patterns, and the two are presented as an either/or choice. The note that `limit` applies only to `for` reinforces the schema's own wording. It adds framing and exclusivity semantics rather than new syntax examples.

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 gives a specific verb plus resource: 'look up recorded practices that address recurring failures,' and further specifies the payload as 'when to use them, evidence and proving instruments.' It explicitly marks the counterpart sibling ('Use failures for the corresponding mistake patterns'), so an agent can separate the success-pattern corpus from the failure-pattern corpus. It stops short of 5 because the tool name 'successes' is opaque on its own and the description leans on internal jargon ('moves', 'proving instruments') that an outside agent must infer.

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 states the two retrieval modes and when each applies: 'Scope by file or task with `for`, or by pattern `id`,' which tells the agent which parameter to reach for in a given situation. It also names an explicit alternative: use `failures` for mistake patterns. There is no explicit when-not guidance (e.g. when the lookup is unnecessary or when another sibling such as `proof` or `route` is preferred), which keeps it at 4 rather than 5.

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