Skip to main content
Glama
Sign In
batch-coverage

batch-coverage

by corner123
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

audit

Scans current inputs and outputs to verify frozen batch coverage and artifact validity, reporting missing, duplicate, unexpected, or malformed IDs and returning PASS, FAIL, or INPUT_CHANGED.

Instructions

Freshly scan actual inputs and outputs; return PASS, FAIL, or INPUT_CHANGED.

Reports missing/duplicate/unexpected IDs and invalid artifacts. PASS means only complete coverage and declared format checks, not correct content. INPUT_CHANGED means this frozen batch no longer describes the input. This does not modify source/output artifacts or force the agent to continue working.

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": {
      "batch_id": "<batch_id>"
    },
    "name": "audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
batch_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose key traits: it is a fresh rescan (not cached), it does not modify source/output artifacts, and it does not force the agent to continue working. That covers side-effect and workflow-advancement concerns well; it omits cost/latency and whether it is safe to call repeatedly.

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?

Front-loads the verb and return codes in the first clause, then spends the remaining sentences on result semantics. Each sentence adds information, though the phrasing 'declared format checks' and 'force the agent to continue working' are slightly opaque.

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?

An output schema exists, yet the description still usefully explains the enum meanings, which is the main thing an agent needs here. Mutation and workflow side effects are covered; the remaining gap is how batch_id is obtained and how this tool relates to its three siblings.

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?

There is a single parameter, batch_id, at 0% schema coverage, so the description must compensate. The phrases 'this frozen batch' and 'frozen batch' weakly imply batch_id identifies a frozen input batch, but there is no statement of format, where the ID comes from, or whether it must come from freeze_inputs.

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?

Names a specific verb ('Freshly scan') and resource ('actual inputs and outputs') and states the three possible outcomes (PASS, FAIL, INPUT_CHANGED). It implicitly separates itself from freeze_inputs by stating it does not modify source/output artifacts, but it never contrasts itself with the sibling 'status' or 'pending' tools, so differentiation is only partial.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description defines what each result code means ('PASS means only complete coverage and declared format checks, not correct content'; 'INPUT_CHANGED means this frozen batch no longer describes the input'), which guides interpretation. However it never says when an agent should call audit rather than status or pending, leaving the choice to inference.

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

Deploy Server

Other Tools