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

The description adds substantial context beyond the annotations: edits apply to the same project, no render or billing occurs, "latest" resolves to the newest project, and the return envelope is spelled out including the empty-applied failure signal and cost fields. What it does not disclose is the destructive side the annotations flag (destructiveHint=true) — whether an edit overwrites or discards existing scenes, captions, or settings, and whether it is reversible.

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 most decision-relevant facts (free, plain-words edit, no render, same project) in one sentence, followed by tight Args/Returns blocks. The Args section partially restates the schema, but it is short and the Returns block earns its space by documenting the empty-applied case.

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 two-parameter mutation tool with no output schema, the definition covers invocation semantics, the default value, the success and no-op return shapes, and cost implications. The only unaddressed complexity is the destructive/reversibility question, which is partly covered by annotations.

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 0% schema description coverage, the description carries the parameter burden and largely does: instruction is defined as "what to change, up to 500 characters" and project_id as "a project id, or 'latest' (default)", with "latest" explained as the newest project. The only gap is no guidance on id format or what happens if the id is unknown.

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 and resource ("Change a project in plain words") with concrete instruction examples ("shorter hook", "bold captions"). It also scopes the operation against neighbors by noting that nothing renders or bills and that it edits the SAME project, so an agent can distinguish it from studio_render or studio_create_project without opening a 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?

Usage is implied rather than stated: you give a natural-language instruction when you want to modify an existing project, and project_id may be "latest" for the newest one. There is no explicit when-not guidance and no named alternative (e.g. studio_patch or studio_assist) telling the agent which sibling to pick for structured field edits versus word-based edits.

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