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

Annotations only declare it as a non-read-only, non-destructive, open-world write; the description adds cost ('Paid (3 casting images)'), asynchronous behavior ('made in the background'), a hard capacity limit, an edge-case side effect on two-lead pre-cast-v2 series costing 4 more images, and a pricing escape hatch via dry_run. That is substantial disclosure beyond what the structured fields carry.

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-loaded with the operation and cost, then constraints, then the side-effect caveat, then dry_run. Every clause carries information, though the telegraphic register ('next id c to h', '4 more images') verges on cryptic for a first read.

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?

Given 13 parameters at 0% schema coverage and no output schema, this is only partially complete: creation mechanics and cost are well covered, but most input fields and how to poll completion (get_run_status given asynchronous generation) are absent. The agent knows the price and the limits, not how to fill half the 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 description coverage is 0% across 13 parameters, so the description must compensate, and it does for the hardest one: relationships is documented as [{to: id or name, kind}] with a minimum-cardinality rule that the bare anyOf/array schema cannot convey. dry_run pricing is also explained. The remaining ten parameters (age, look, outfit, palette, body_type, gender, name, series_id, function, voice_note, signature_prop) get no semantics at all, which holds it below 5.

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 (add a recurring character) plus the concrete artifacts produced: face, full body, turnaround. The cast-size and id-range clauses ('next id c to h, 8 in the cast at most') make it immediately distinguishable from recast/recast_lead and list_characters.

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?

Implied context is clear (creating a new cast member as opposed to recasting an existing one), and the 'at least one to a lead' relationship constraint plus the cast cap of 8 are real preconditions. However, no sibling is named and there is no explicit 'use recast_lead if the character already exists' routing, so the agent must infer the boundary.

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