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

The description goes well beyond the annotations (which only say readOnlyHint=false, destructiveHint=false, etc.) by disclosing honest limits: video overlay audio does NOT play (silent), overlays render above footage but BELOW captions, and they do NOT track objects. It also explains the behavioral difference between fit='cover' and insert_media regarding program timing. This is rich behavioral context that an agent needs to set expectations correctly.

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 and information-rich, with clear section markers (PROJECT-SCOPED, HONEST LIMITS). It front-loads the most important scoping constraint and the primary use case. It is long, but every sentence adds operational value—defaults, ranges, exclusions, and behavioral caveats. Slightly over-long for a quick scan, but the structure (caps for key phrases, bullet-like clauses) helps navigation.

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 13-parameter tool with no output schema and only 15% schema coverage, the description is remarkably complete. It covers parameter semantics, defaults, ranges, behavioral limits, and the key sibling distinction (insert_media). It even addresses asset sourcing (list_assets) and reuse policy. Nothing an agent needs to invoke this tool correctly 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 description coverage is only 15%, so the description carries the burden of explaining parameters. It does this thoroughly: duration_s defaults (image 4s, video clip's length bounded by program end), x/y as CENTER fractions (ignored with fit='cover'), keyframe list format [{t,v}] for drift/slide, scale as fraction of frame width with range and default, opacity range, entrance/exit enums, source_start_s for seeking. This is far beyond what the schema provides.

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 clearly states the tool's function: drawing an image or video clip over the program picture for a window of PROGRAM time, with specific use cases (picture-in-picture, corner logo, b-roll cutaway). It distinguishes itself from insert_media by explicitly noting that insert_media PAUSES the talk and adds time, while fit='cover' does not. The verb 'draw' and resource 'overlay' are specific and unambiguous.

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 explicit when-to-use guidance: 'THE way to show what the speaker is talking about without touching the timing.' It also gives a clear exclusion: 'insert_media PAUSES the talk and adds time; fit='cover' does not — pick by whether the speech should continue.' This directly helps an agent choose between add_overlay and insert_media. It also mentions asset_key from list_assets, providing a source for valid inputs.

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