script_patch

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

Description adds critical safety behavior beyond annotations: 'Atomic + safe: nothing is written if any anchor is missing/ambiguous or (for .gd) the result fails to compile.' Annotations only indicate destructiveHint=true; description provides detailed failure conditions and atomicity, fully informing the agent of risks.

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, front-loaded with purpose. Every sentence delivers value: purpose, parameter details, safety guarantees, and usage guidance. No wasted words.

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?

Covers the complex input format and safety, but omits what the tool returns (e.g., success/error). Since there is no output schema, a brief note on return value would improve completeness. Otherwise, the description is thorough for a mutation tool.

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?

With 100% schema coverage, description adds substantial meaning: explains the edits array format (find/replace/all, append, prepend), the constraint that 'find must match EXACTLY once unless all:true', and that path must be 'existing'. This greatly enhances agent understanding beyond 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?

Clearly states 'Surgically edit an existing res:// file' with a specific verb and resource. Distinguishes from sibling 'write_script' by noting preference for small changes, making the tool's unique role clear.

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?

Explicitly advises 'Prefer this over write_script for small changes,' giving context for when to use this tool vs. an alternative. Does not explicitly mention when not to use (e.g., for large rewrites), but the preference statement strongly implies it.

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