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

Annotations (readOnlyHint=true) already indicate safety, but the description goes well beyond by disclosing cost ('Nothing is charged and no GPU is rented; it spends a little of Kleo's daily planning quota'), intentional nondeterminism ('Two identical requests get two different treatments on purpose'), and its interrogation behavior ('reads language, length and format off the request first and asks only for what is missing'). No contradiction with 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?

The description is long but justifiably so for a tool with 11 parameters and a complex workflow. It is front-loaded with the core purpose and step position, then flows logically into behavioral notes and handoff instructions. Every sentence adds information; there is no padding or repetition of schema content.

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 the tool's complexity (11 params, no output schema), the description fully covers the workflow: what it produces, how it behaves, what the caller must do with the result (tell the user logline and decisions, pass the treatment object to kleo_create_video), and the consequences of not using it. It also explains the author parameter's tradeoffs. Nothing an agent needs to invoke it correctly is 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 coverage is 100%, so the baseline is 3. The description adds value by clarifying the resolution strategy for several parameters: it reads language, length, format off the request and asks for missing ones, and for music, subtitles, and format it explicitly says to 'pass their answer, never a guess.' This goes beyond the schema's field descriptions and helps the agent use parameters correctly.

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 states a specific verb ('turns the user's request into the TREATMENT'), names the resource (the film treatment), and clearly distinguishes from siblings by labeling itself 'Step 1 (recommended)' and explaining its relationship to kleo_create_video. It also highlights a unique behavioral trait ('Two identical requests get two different treatments on purpose'), leaving no ambiguity about its role.

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 gives when-to-use guidance ('Step 1', 'call it once per video'), what to do with the output ('pass the returned treatment object ... to kleo_create_video'), and what happens if skipped ('Kleo writes a treatment itself while planning, and the user never sees it first'). It also provides a conditional alternative for the author parameter ('use only if you cannot write JSON yourself').

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