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

Goes well beyond the annotations: it discloses that writes repair certain mistakes automatically and report each repair, that a non-compiling write writes nothing (atomic), that branchId writes a version without switching the editor, and the skill-loading contract. These are exactly the behavioral traits an agent needs and none are derivable from readOnlyHint/destructiveHint/idempotentHint.

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 core purpose, repair and branchId semantics are front-loaded and tight, but the long inline catalogue of eleven skills and their triggers bloats the description considerably. Most of it is actionable, yet it reads as a reference list rather than lean routing text.

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 three-parameter, no-output-schema mutation tool this covers a lot: atomicity, auto-repair reporting, skill prerequisites, branchId behavior, and a note that film is XML rather than TS/JSX. What is missing is explicit differentiation from sibling edit tools and any mention of limits on replacement size or count.

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 schema coverage at 67%, the description usefully reinforces and extends parameter meaning: find must match byte-for-byte, replace empty deletes the span, all=false requires a unique match, branchId null means current version. It largely duplicates the branchId schema text but adds real semantics for the replacements sub-object.

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 opening sentence gives a specific verb and resource: apply exact replacements to main.film in one compile. It also conveys the atomic/repair mechanism that separates it from a plain text replacer. It does not explicitly contrast with close siblings like fix_film or replace_film, so an agent must infer the boundary.

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?

Provides real precondition guidance: load required skills before the first write that touches a given feature, all in one load_skill call, and explicitly exempts value-only patches from any skill. Also clarifies branchId null vs a list_branches id. However it never states when to choose patch_film over fix_film/replace_film/check_film, which is the most consequential routing decision here.

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