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

With no annotations, the description carries the burden and does well: it discloses the quota (up to 10), how the photo is processed ('saved as it is, padded onto white'), and the draft default. It does not say what happens if the name already exists or whether saving costs credits, which are the remaining behavioral gaps.

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?

Three sentences, front-loaded with the core action and the source options, with no filler. The middle parenthetical about photo handling is dense but earner-placed; minor cost is that it packs two ideas into one long clause.

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?

Covers the full lifecycle an agent needs: where the image comes from, the quota, and how the saved name is reused in create_video. Missing only edge cases (duplicate-name handling, overwrite vs error) for a mutation tool with no annotations or output schema.

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 baseline is 3, but the description adds the relationships the schema does not: image_url is specifically for a non-latest draft, photo_url substitutes for a generated picture, and omitting both means the current draft. That mode-selection logic is genuine added meaning.

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 ('Save a character to the user's library under a name') and immediately enumerates the three sources, which distinguishes it from siblings like draw_character, create_character, and change_character.

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 tells the agent which input selects which mode: no image/photo params means the current draft, image_url picks a specific non-latest draft, photo_url saves the user's own photo. It also states the 10-character quota and the downstream step (pass the name as `character` to create_video).

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