Compose cue list (NL → setlist)

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

The description discloses the LLM vs deterministic parser fallback, which is a behavioral trait beyond the annotations. It also mentions optional chaining into create_cue_sequencer, indicating potential side effects. Annotations already cover readOnly/destructive hints, so this adds value.

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?

Three sentences, front-loaded with purpose, no redundant content. Every sentence adds information about behavior or chaining.

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?

The tool has 8 parameters but all are well-documented in the schema. The description clearly states input, output (via schema hint), and fallback/chaining behavior. It lacks explicit return format but is adequate given no output 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 has 100% coverage, so baseline is 3. The description adds context for apply/containerName by mentioning optional chaining, and for preferLlm by discussing the LLM vs grammar parser. This elevates to 4.

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 uses a specific verb 'turn into' and identifies the resource (natural-language show description → validated cue list). It distinguishes from siblings by naming the specific schema variant (scenes[]) and explicitly referencing create_cue_sequencer as a downstream chain.

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?

The description implies usage context (NL show description to cue list) but does not provide explicit when-to-use vs alternatives, nor exclusions. It mentions the LLM/grammar fallback and optional chaining, which are behavioral details rather than usage guidelines.

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