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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, and the description adds substantial behavioral detail: project-scoped action, return of project identity, preview without encoding, audio/cuts unchanged, exact replacement text, and the effect of each operation (e.g., replace clears the entire set). No contradiction with annotations.

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 dense but every sentence contributes necessary information. It front-loads the scoping constraint and then logically explains operations and parameter formats. Slightly long but appropriate for the tool's complexity; no wasted words.

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 four parameters, multiple operations, low schema coverage, and no output schema, the description covers all necessary aspects: operations and their effects, parameter formats, scoping requirement, return behavior (preview without encoding), and non-destructive nature. An agent has enough to call it correctly.

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 description coverage is only 25% (only project_id has a description), yet the description fully explains the semantics of operation, clear, and replacements, including the accepted formats for replacements ([from,to] pairs or objects with optional start/end). This compensates completely for the low schema coverage.

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 states a specific action ('Edit displayed captions') and details the operations (replace, append, clear, list), making it clear what the tool does. It also differentiates from siblings by emphasizing project-scoping and that it affects only caption text while leaving audio/cuts unchanged, distinguishing it from style or mute tools.

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 provides clear context for when to use this tool (editing caption text) and mentions that it acts only on the explicit project_id, but it does not explicitly name alternatives or state when not to use it (e.g., for style changes use set_caption_style). The guidance is implied rather than explicit.

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