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

Adds substantial context beyond the annotations: it costs one generation of the publisher's credits (text for heroes, image or music for the rest), takes ~2 minutes before a retry is warranted, that a retry with generation_id is free, and that the asset is appended to package.assets and occupies the given slot. Those side effects and cost/auth facts are not derivable from readOnlyHint=false / openWorldHint=true.

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?

Purpose is front-loaded and nearly every clause carries information (cost, retry, slot mechanics, validation hand-off). It is dense and semicolon-chained rather than structured, which costs some scannability, but no sentence is filler.

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 10-parameter, nested-object, no-output-schema tool, it covers the return shape (updated package and its link), cost, timing/retry, and pre-publish validation. Remaining gaps are failure modes (what happens if generation fails outright) and the meaning of tier/base_set, which the schema only gestures at.

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 100%, so the baseline is 3; the description still adds meaning, explaining slot syntax (cast[0], set, music), what `package` is and where it comes from, and elaborating each kind beyond the schema's terse enum string. It does not explain `tier`, `base_set`, or `style` beyond what the schema already says.

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+resource (generate an asset for a video) and enumerates the six asset kinds with a parenthetical gloss for each (voxel hero CharacterSpec recipe, rig recipe, cut-out, prop, scene, loop). It also distinguishes itself from the generic generators by tying output to the studio's asset format and the `package` from plan_video.

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 clear context: run after plan_video, pass the plan item's slot, retry with the same kind + generation_id after ~2 minutes, and check hero recipes with validate_asset before publishing. It also points at estimate_media_cost for budgeting. It never explicitly excludes sibling generators like generate_image/generate_music/generate_text, which would have made this a 5.

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