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

Goes far beyond the annotations: states credit price by subject type, that credits are captured upfront and fully refunded on failure, partial-success behavior with `partial: true` and `missingViews`, partial charging with `creditsCharged`, typical latency, face-consistency behavior across views, and content-policy rejections with no charge. The annotation profile (not read-only, idempotent, open-world) is consistent with this and the description supplies the operational detail annotations cannot.

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?

Front-loads the purpose, output shape and price before costs and edge cases, and nearly every sentence carries distinct information. It is dense to the point of being a single breathless block, so a small amount of structural separation would improve scanability.

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 fully compensates by describing the return payload (`partial`, `missingViews`, `creditsCharged`, images included inline), failure modes, and the refund rule. An agent has everything needed to call it, set expectations with the user, and interpret 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 baseline is 3; the description adds real meaning by tying `subjectKind` to pricing (21 vs 10 credits) and to view-consistency behavior, explaining the default of 5 for `imageCount`, and justifying `idempotencyKey` as retry protection. It does not explain the `description` field's 8-400 char constraints, but the schema already does.

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 ('Make a character sheet for one of your series') plus the exact output ('4-6 AI images ... of ONE fictional character, from a text description'). The 'ONE character' emphasis and the enumeration of views distinguish it cleanly from sibling tools like autoshort_create_character_episode and autoshort_select_character_image.

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 an explicit prerequisite ('call autoshort_get_character_sheet first and tell the user'), a hard quota ('A series can hold 3 sheets in total; the first sheet is chosen automatically'), and a clear exclusion list of rejected inputs. It does not, however, contrast itself with the adjacent episode-generation sibling, leaving that routing implicit.

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