script_patch

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

Annotations mark this as destructive, and the description correctly aligns by describing an edit operation. It goes beyond annotations by disclosing atomicity ('Atomic + safe') and the guarantee that 'nothing is written if any anchor is missing/ambiguous or (for .gd) the result fails to compile', which is valuable for an agent assessing failure modes.

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 three sentences: purpose, data format, and safety/usage guidance. Each sentence is information-dense 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 tool with complex nested edit items, the description covers the input format, constraints, failure behavior, and guidance for alternative tools. It does not explain return values, but no output schema exists and the behavior (success/failure) is implied by the atomic guarantee.

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?

The schema provides brief descriptions for path, edits, and validate, but the description adds crucial detail: the exact structure of edit items ({find, replace[, all]}, {append}, {prepend}), the 'find must match EXACTLY once unless all:true' constraint, and the compile-check behavior of validate (default true, .gd only). This substantially enriches the schema information.

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 'Surgically edit an existing res:// file without rewriting it whole', which specifies a clear verb (edit), resource (res:// file), and scope (existing file, targeted edits). It explicitly contrasts with write_script, distinguishing itself from a sibling tool.

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 'Prefer this over write_script for small changes', directly telling the agent when to choose this tool over an alternative. It also implies that large rewrites should use write_script, and the atomicity warning gives context for safe usage.

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