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

Annotations only cover the safety profile (not read-only, not destructive, not idempotent). The description goes well beyond: it discloses that one undo reverts the operation, that the created clips share a captionGroupId and can be restyled as a group, that the tool returns created clip ids, and — most valuably — the non-obvious track-placement behavior (joins existing caption tracks when they fit, opens a new one on overlap, joins the LOWEST caption track so later b-roll can occlude them). These are exactly the behavioral traits annotations cannot express.

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 purpose in the first sentence, then layered with placement and rendering details. Every sentence carries real information, but the paragraph is dense and long for a single tool, with track-placement lore that could be tighter. Efficiency is good, hygiene could be better.

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?

No output schema exists, and the description compensates by stating the return value ('Returns the created clip ids'). Preconditions, side effects, follow-up tooling, and the subtle rendering-behind-b-roll hazard are all covered, leaving nothing an agent needs to know before invoking it.

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 100%, so all nine parameters (preset, position, textCase, censorProfanity, maxWordsPerCaption, etc.) are already documented in the schema. The description adds no parameter-level meaning beyond what the schema provides — it never mentions the styling options or word-grouping controls. Baseline 3 is appropriate when the schema does all the parameter work.

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 ('Generates animated captions from a spoken clip's transcript') and immediately scopes the input ('a spoken clip'). It distinguishes itself from siblings by naming the preconditions (get_transcript) and the related follow-up tools (set_clip_properties, manage_tracks), so an agent knows exactly what this tool produces versus what neighboring tools do.

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?

Explicitly states the prerequisite ('Needs a transcript (get_transcript tells you)'), names the alternatives for follow-up work (restyle via set_clip_properties with text.wholeCaptionGroup; tidy via manage_tracks {action:'tidy'}; merge via manage_tracks {action:'merge'}), and even explains when NOT to tidy up after captioning. This is a genuinely strong routing guide.

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