Generate a unified diff between two text versions (the before and after). Returns the diff text plus metrics (lines added, lines removed, output chars). Requires a valid API key (Bearer token); billing is per combined input characters. To apply a diff, use patch.
| Name | Required | Description | Default |
|---|---|---|---|
| text_a | Yes | First text version (the "before" text). | |
| text_b | Yes | Second text version (the "after" text). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite safe annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds meaningful behavioral context: authentication via Bearer token, billing per combined input character, and the return shape including metrics. This goes well beyond what annotations alone convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each earning its place: the core operation, the return value, and the auth/billing/alternative guidance. The most important information is front-loaded, with no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter, side-effect-free tool, the description covers inputs, output format, authentication, billing, and the key alternative. Since there is no output schema, disclosing the returned metrics is especially valuable and makes the tool self-sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema fully documents both parameters. The description mostly repeats the before/after semantics already present in the schema, adding no new parameter-specific meaning. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Generate a unified diff between two text versions.' It clearly identifies the inputs (before/after) and differentiates itself from the sibling `patch` by explicitly stating that applying diffs is a separate operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says when to use this tool (to generate a diff) and explicitly names `patch` as the alternative when the goal is to apply a diff. It does not address every sibling, but the key alternative is clearly distinguished.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool performs a distinct operation: conversion, diffing, patching, pruning, llms.txt generation, validation, and cost estimation. The descriptions explicitly cross-reference related tools (diff/patch, generate/validate), which further prevents misselection.
All seven tools use lowercase single-word imperative verbs (convert, diff, estimate, generate, patch, prune, validate), forming a consistent and predictable naming convention.
Seven tools is within the ideal range and every tool has a clear purpose. The set is compact rather than sprawling, with no redundant or filler tools.
The paired workflows are complete: diff/patch, generate/validate, and convert/prune cover their stated operations without dead ends. The main gap is that the estimate workflow points to an external pricing endpoint for supported models rather than exposing model/pricing lookup as a first-class tool, which is a minor obstacle.