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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description is free to add domain behavior — and it does: each character is a single kit sheet with five specific views in a base outfit, created via start_character, scoped to one artist's kit, and optionally shared to every other artist's videos via update_kit_piece. That is real context an agent cannot get from the 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 text is a run-on block with a missing sentence break ('your cast Each character') and no front-loading of what the tool returns; it reads as internal design notes rather than a scannable definition. It is information-dense, but the density is buried in parenthetical asides about sheets, outfits, and missing views.

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 usefully discloses the returned fields (owner_artist_id, owner_name, shared, outfit, missing) and what 'missing' means, which is exactly the gap a 3-param list tool with no output schema would otherwise have. Only the return ordering/grouping semantics ('theirs first, then shared') live in the schema rather than the description.

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 a 3 is the floor, but the description genuinely adds relational meaning: setting artist_id yields that artist's single character, whereas the unfiltered case returns cast members addressed by handle, and it explains owner_artist_id/owner_name ownership semantics and the shared flag. The wording is terse enough that the mapping to for_artist_id is only implicit.

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 opening fragment 'The people videos can show: your artists' characters and your cast' identifies the resource domain (characters/cast) but never states the verb or that it returns a list — the agent has to infer 'list' from the name. It also does not distinguish this from siblings such as list_kit, get_kit_piece, or list_artists, which plausibly return overlapping data.

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?

There is no explicit when-to-use or when-not guidance and no routing to alternatives (list_kit, get_kit_piece, list_artists). The closest thing is an implicit context ('the people videos can show'), plus a parenthetical pointing at start_character and update_kit_piece, but those are creation/sharing tools, not alternatives for retrieving characters.

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