Skip to main content
Glama

Fix a heavy machine-file chain

fix_machine_chain
Read-onlyIdempotent

Use after a scan reports MACHINE_CHAIN_HEAVY (crawlers must read too many or too large files before the page). Returns a fix plan: the files a crawler reads before the page and the 404s that absent agent files return, then measured reductions (llms.txt to an index, a sitemap index, robots.txt comments and duplicate groups, minified JSON, short 404s) with the chain size after each step and the step at which the finding stops firing. Read-only; changes nothing on the site. Give domain (uses the latest scan on file) or a report id. For other findings use explain_finding.

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": "fix_machine_chain"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoReport id
domainNoUses the latest scan on file

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, destructiveHint=false, idempotentHint and openWorldHint, and the description reinforces this with 'Read-only; changes nothing on the site.' It adds genuinely non-obvious behavior by spelling out that the output is a plan rather than a mutation, including the sequence of measured reductions and where the finding stops firing. It does not cover failure modes (e.g. what happens if no scan exists for the domain), which keeps it off a 5.

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 trigger condition is front-loaded in the first clause, followed by return contents, then invocation modes, then the alternative — a sensible order. The parenthetical list of reduction types (llms.txt index, sitemap index, robots.txt comments, minified JSON, short 404s) is dense but each item is informative rather than filler; a single sentence runs long.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description fully characterizes the return value: the pre-page file list, the 404s, each reduction step with post-step chain size, and the step where the finding clears. Combined with the trigger, alternatives and input modes, an agent has everything needed to call this correctly.

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, but the description earns extra by clarifying the either/or contract between 'domain' and 'report id' even though required-parameters is zero, and by restating that domain resolves to the latest scan on file. That resolves real ambiguity about what to supply.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific trigger ('fix' after a MACHINE_CHAIN_HEAVY finding) and a concrete resource (the machine-file chain crawled before the page), and states exactly what the call yields: a fix plan with files, 404s and measured reductions. It is clearly separable from sibling fixers (fix_robots, fix_entitymap) and from explain_finding, which it explicitly routes away.

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

Usage Guidelines5/5

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

Gives an explicit precondition ('Use after a scan reports MACHINE_CHAIN_HEAVY'), names the alternative for other findings ('For other findings use explain_finding'), and tells the caller the two accepted invocation modes (domain for latest scan, or a report id). Nothing about when to pick this tool is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.