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

Goes well beyond the annotations: it discloses the conditional-write guarantee ('writes only when the result has no more errors than before'), the reporting behavior ('reports each repair and what still needs an edit'), and the precise semantics of unsafe including concrete examples of guesses. This is exactly the context annotations cannot carry.

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?

Front-loaded with purpose and the sibling contrast, then layered behavioral guarantees, then parameter semantics. Dense but every sentence carries distinct information 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?

With no output schema, the description verbally covers the return profile (each repair plus outstanding edits), and it covers the mutation safety story and version targeting. Nothing an agent needs to call this tool safely is missing.

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 baseline is 3, and the description still adds value: concrete examples of what counts as a 'guess' under unsafe, and the branchId 'fixes that version' behavior. Some overlap with the schema text keeps it from a 5.

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?

States a specific verb+resource ('Autofix main.film') and immediately distinguishes itself from the two closest siblings, patch_film and replace_film, by naming what those tools do and how this one differs. An agent can route between the three without opening any schema.

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 gives when-to-use ('problems the film already had, which a write reports and leaves alone') versus when the siblings apply, and adds conditional guidance for the unsafe flag ('Leave it false unless the report names a guess you want'). No inference required.

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