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

Annotations already declare a non-read-only, open-world, non-idempotent, non-destructive call, and the description adds real behavioral facts on top: a 2-credit cost, that the output is exactly two portraits, that a photo is downloaded once, and that real-person photos require consent. It does not cover failure modes or what happens if consent is missing despite a photo being supplied.

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?

Two dense sentences that front-load what the agent gets (two portraits) and then the follow-up action. The phrasing is slightly telegraphic ('who, age, look, or from a real person's photo with consent'), but nothing is padding.

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 carries the return-value burden and does state that two portraits come back plus the credit cost and the consent precondition. The lifecycle is adequately covered; only the edge cases around an unsaved character and consent rejection are missing.

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 60%, and the description echoes the field intents (look, age, photo with consent), so it adds a little framing but no syntax or format detail beyond the schema. The 'who' mapping to the gender parameter is left implicit, and gender is never named in prose.

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 says the tool produces 'two portraits of a recurring person for the brand' and enumerates the dimensions it controls (who, age, look, or a consenting real person's photo), which is a concrete verb+resource. It partially distinguishes itself from image-generation siblings by naming save_character, generate_clips and remake_from_reference, though it never explicitly contrasts with create_image or generate_photos.

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 lays out the downstream workflow explicitly ('Then save_character with the portrait you like') and explains why a character_id matters for generate_clips and remake_from_reference. It stops short of stating when NOT to use this versus create_image/generate_photos, so it is clear context rather than full when/when-not guidance.

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