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

Adds meaningful behavior beyond readOnlyHint: 'Free text generation, no images or credits spent' and describes the returned entry fields and their semantics. It does not discuss latency, determinism, or limits beyond those in the schema.

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?

Dense but front-loaded: purpose first, cost/no-credits note second, return shape third, parameter behavior fourth, downstream usage last. 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?

With no output schema, the description compensates by naming the return keys (titel, bild_en, bewegung_en) and their semantics ('one moment and one strong action each'). Combined with the cost note and downstream usage, an agent has enough to call it correctly.

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 real meaning for 'figur': it accepts a character-sheet id and uses that sheet's prompt_prefix_en, or a free-text character description, going beyond the schema's brief text.

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: 'Suggest independent visual gags for a character and theme.' It also explicitly distinguishes the output from a story sequence ('no story sequence or references between entries'), which differentiates it from downstream storyboard siblings.

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 a clear downstream use case: 'Select 8–16 suggestions for lab_auto_storyboard with figur_id.' It also clarifies intended output scope ('no story sequence'), but does not explicitly name when not to use it or compare against other ideation siblings beyond the downstream link.

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