Save a creator

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

With annotations limited to default false flags (readOnlyHint false, destructiveHint false), the description carries the behavioral burden and delivers: it discloses the persistence side effect (creator appears in list_creators), the cost profile ('Saving is FREE and renders nothing'), and the consent policy ('never assert that on their behalf'). No contradiction with annotations — readOnlyHint false is consistent with a write operation.

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 but front-loaded with the core purpose, and the 'LIKENESS —' section break organizes the parameter guidance. Every sentence carries actionable information, though the length is substantial and there is slight redundancy with the schema text for image and name.

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 7-parameter tool with no output schema and sparse annotations, the description covers purpose, prerequisites (upload_file for local files), side effects, cost, and consent constraints thoroughly. The only gap is that no direct return value is described, though 'from then on list_creators returns them' partially compensates by telling the agent how to verify the result.

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 adds meaningful semantics beyond the schema, particularly for source ('leave it "generated" for an AI-made person, and use "upload"/"social" ONLY for a REAL person') and consented ('only when the user has told you that person agreed to their likeness being used'). This elevates it above the schema-only baseline.

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 uses a specific verb and resource — 'Add a portrait to this workspace's reusable CAST so the SAME person can star in future ads' — and explains the persistence effect. It distinguishes itself from siblings by naming its downstream consumers (list_creators, generate_avatar, generate_video, recast_motion) and referencing the app's picker-save flow, so an agent can tell it apart from related creator tools.

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?

It provides clear workflow context: pass a public url, use upload_file first for local paths, and after saving use the url with the listed generation tools. It also gives strong conditional rules for source and consented. It does not explicitly name a when-not-to-use alternative, though no direct sibling substitute for saving a creator exists.

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