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

Goes well beyond the annotations: states that spans is a COMPLETE replacement list (not additive), that spans=[] restores all captions (reversibility), that audio and the cut are untouched, and that the call is project-scoped and returns project identity. This clarifies the replace-vs-append semantics that the annotations' idempotentHint alone would not 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 project-scope constraint and the core action, and each clause carries real information. Slightly long due to the enumeration of excluded element types, and 'PROJECT-SCOPED' is partly restated later, but nothing is truly wasted.

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 still tells the agent what comes back (project identity), how state is affected (replacement, reversible via empty list), and what is unaffected (audio, cut). Nothing material for correct invocation 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 only 50% (spans has no schema description), but the description fully compensates: nested [[start, end], ...] array shape, program-seconds unit, and full-replacement semantics including the empty-array case. That is exactly the information the bare schema omits.

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?

Names a specific verb and resource ('hide the burned spoken-word captions') plus the precise scope ('over specific PROGRAM-time windows, leaving them on everywhere else'). Clearly separable from siblings like set_caption_style, set_caption_fixes and erase_burned_text because it modulates visibility of already-burned caption text rather than styling or removing 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?

Gives an explicit trigger ('for when a full-frame effect, a graphic or a text treatment would otherwise have captions burned across it') and explicit exclusions ('Not needed for inserted media or title cards ... nor for motion graphics'). The agent knows both when to reach for it and when to skip it.

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