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

Annotations already mark it read-only/non-destructive; the description adds the crucial clarification that despite 'switch framework' wording it returns local source and does not render, save or upload, and that the project is caller-held rather than a hosted saved project. It also discloses rejection behavior ('a rejected field is unsupported in both frameworks'), which the annotations cannot convey.

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 the core action, then usage rules, then the iteration loop, then the non-goals. Dense and nearly waste-free, though the framework-inference warnings are repeated in spirit across two sentences.

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 and nested project/spec objects, the description supplies the needed context: what is returned (local source and commands), what is not (render/save/upload), and how to iterate. It doesn't describe the shape of the returned source/commands, which is a minor remaining gap.

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 meaning beyond the schema by explaining the framework field's intent (never infer from creative wording, omit unless the user chose, ask on needs-selection) and the spec/project relationship. It does not explain the mutual exclusivity of spec vs project explicitly, leaving a small gap.

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 pair: validate one VideoSpec against the paired template contract and return local source for a chosen framework, or switch an existing project's framework. It is clearly distinguishable from siblings like scaffold_video_spec or get_template, and even names the input artifact (VideoSpec) that selects it.

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?

Explicit routing rules: 'For a VideoSpec template in Remotion or HyperFrames, use prepare_video_template with the VideoSpec', plus when not to infer a framework, when to omit it, and to ask the user on needs-selection. It also prescribes the follow-up loop (edit project.spec, call again to regenerate or switch).

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