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

Annotations only say readOnlyHint=false and destructiveHint=false. The description adds substantial behavior: the tool is free, asynchronous, returns a job_id, refuses non-FilmLab material before doing anything, charges nothing, and requires human confirmation before pricing. These are meaningful operational details beyond the annotations.

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 step number and cost status, then purpose, inputs, refusal behavior, async flow, and next step. Despite its length, every sentence carries actionable information.

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 an asynchronous two-step planning tool with no output schema, the description covers the full workflow: inputs, validation failure, job polling, next tool, pricing step, and cost safety. Nothing essential is missing for correct invocation.

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 parameter definitions are already strong. The description still adds useful provenance and constraints, notably that foto_url should be a FilmLab-generated reference such as a character sheet view and that uploaded clips or photos are refused.

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: it finds a person in a generated clip and plans which face stretches to redraw. It also distinguishes itself as step 1 of 2 and names the follow-up sibling lab_face_fix_freigeben, so an agent can separate it from related tools immediately.

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 says when to use it, what inputs to provide, what is refused with face_fix_nur_generiert, and what to do next (poll lab_get_job, then call lab_face_fix_freigeben with get_cost). Alternatives and sequence are fully covered.

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