Skip to main content
Glama
Sign In
batch-coverage

batch-coverage

by corner123
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

freeze_inputs

Freeze actual input IDs and hashes before batch processing, then return a new batch_id for auditing outputs and resuming missing or malformed results.

Instructions

Freeze actual input IDs and hashes before batch processing; return a new batch_id.

Paths must be inside the configured workspace. Files map to JSON objects at {relative}.json under a dedicated output directory. JSONL uses nonempty string IDs at id_field. Never shrink the user's input scope just to pass an audit. This writes audit state only, never source or output artifacts.

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": {
      "kind": "<kind>",
      "input_path": "<input_path>",
      "output_path": "<output_path>"
    },
    "name": "freeze_inputs"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
id_fieldNoid
input_globNo**/*
input_pathYes
output_pathYes
output_templateNo{relative}.json
required_fieldsNo

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 a good job: it declares the write scope ('writes audit state only, never source or output artifacts'), the workspace path restriction, and the two distinct modes of file-to-object mapping. It omits whether freezing is idempotent or what happens on re-freeze of the same inputs.

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?

The core action and return value are front-loaded in one sentence, followed by mode-specific details. Some fragments ('JSONL uses nonempty string IDs at id_field') are terse but every line adds information; nothing is redundant.

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, so return values need not be described. For a 7-parameter mutation tool with no annotations, the description covers scope, safety boundary, and output layout; the remaining gap is the unexplained input_glob and required_fields parameters.

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 0%, so the description must compensate and partially does: it explains output_template's {relative}.json pattern, id_field's nonempty-string-ID requirement for JSONL, and path constraints. But input_glob and required_fields are never mentioned, leaving two of seven parameters unexplained.

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?

States a concrete verb and resource: freeze actual input IDs and hashes and return a new batch_id. That is far more specific than the sibling names (audit, pending, status), but it never explicitly distinguishes itself from 'audit', which is the closest conceptual neighbor.

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 phrase 'before batch processing' gives the trigger condition, and 'Never shrink the user's input scope just to pass an audit' is a useful anti-pattern warning. However, no alternative tool is named and there is no explicit statement of when not to use this versus 'audit' or 'pending'.

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