compress_ai_readme

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

No annotations are provided, so the description carries the full burden. It thoroughly describes the deterministic text transforms, lists specific removals (filler words, verbose phrases, hedging, fluff), explicitly states what is never modified (code blocks, headings, etc.), and notes that output may contain sentence fragments. This is exemplary transparency.

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?

The description is well-organized into sections: a concise summary, 'WHEN TO CALL', 'WHAT IT DOES' with bullet points, and a note about fragments. It is dense but not verbose, with every sentence adding value and front-loading the key action.

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?

Given the tool's complexity (specific transform rules), the description is complete. It explains the compression scope, what is modified, what is preserved, and the nature of the output (sentence fragments intentional). No output schema exists, but the description adequately covers expected behavior.

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 baseline is 3. The description adds value by explaining the 'dryRun' parameter's purpose ('preview changes before writing') and emphasizing its use before making modifications. This clarifies the parameter's behavior beyond the schema.

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 clearly states 'Compress an AI_README.md file using deterministic filler-language removal (no LLM call).' This specifies a specific verb ('compress'), the resource ('AI_README.md'), and the method, differentiating it from siblings like 'init_ai_readme' or 'validate_ai_readmes'.

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 includes a 'WHEN TO CALL' section with explicit triggers: after 'validate_ai_readmes' reports filler-language warnings or high token count, after 'init_ai_readme', or anytime to reduce token footprint. It also recommends using dryRun first, providing clear guidance on tool usage.

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