Skip to main content
Glama
Sign In
criticmarkup

criticmarkup

by Martennnnn
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

request_changes

Proposes a single targeted edit or deletion with CriticMarkup while enforcing the configured cutoff line, so authors can accept or reject the change.

Instructions

Applies a single targeted change or deletion using CriticMarkup. Targeted edits past the configured cutoff line are prohibited.

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": {
      "filepath": "<filepath>",
      "search_string": "<search_string>",
      "replacement_string": "<replacement_string>"
    },
    "name": "request_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
filepathYes
search_stringYes
replacement_stringYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3/5.0
Behavior2/5

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

With no annotations, the description bears the full behavioral burden. It usefully discloses the cutoff-line restriction and that edits are CriticMarkup annotations rather than silent overwrites, but says nothing about what happens if search_string is missing or ambiguous, whether the change is reversible, or what permissions are required.

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?

Two short sentences with no filler, and the core action is front-loaded before the restriction. Slightly terse given the ambiguity it leaves unresolved.

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?

The output schema exists, so return values needn't be explained, and the cutoff-line constraint covers the main behavioral risk. But for a 3-required-param mutation tool with zero schema descriptions, the missing matching semantics and failure behavior leave real gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three required parameters, and the description supplies no meaning for filepath, search_string, or replacement_string. Critically, it doesn't clarify how search_string is matched (literal vs. regex, uniqueness requirement) or what an empty replacement_string means for deletion.

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 specific verb ('applies') and resource ('single targeted change or deletion') plus the mechanism (CriticMarkup). The word 'single' implicitly distinguishes it from siblings like replace_multiple and replace_all, though the differentiation isn't stated explicitly.

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?

It gives one real usage constraint — targeted edits past the configured cutoff line are prohibited — which an agent needs. However, it never says when to prefer this over replace_multiple, replace_all, or write_comment, so sibling selection 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.

Deploy Server

Other Tools