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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds substantive behavior beyond them: it never watches video or judges observation truth, only fixes the representation layer, separates lossless fixes (normalized_patch) from semantic errors, and is advisory rather than authoritative. That is rich context an agent needs to interpret results correctly.

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 key qualifier (FREE preflight) and dense with signal, but the fully duplicated Chinese sentence adds length without adding information for a single-language reader. Structure is otherwise tight with no filler sentences.

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 a 4-param nested validation tool with an output schema, the description is close to complete: it scopes what is and isn't validated and explains the advisory relationship to compile_film_breakdown. Return-value details are correctly delegated to the output schema, so no gap there; only the nested field-level semantics are left to 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%, so the description must compensate; it names all four top-level parameters and assigns each a validation role (cross-referencing shot ids, scene membership, relation endpoints, window completeness for long takes). It does not enumerate the many nested layer/provenance fields, but it covers the parameters that matter for invocation.

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 (validate) and resource (a film breakdown payload of film_manifest + shots + scenes + relations), then enumerates the exact checks: schema shape, closed vocabularies, cross-references, window topology, provenance, observability metadata. It explicitly distinguishes itself from compile_film_breakdown as the non-authoritative preflight.

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 explicit when-to-use guidance ('compile_film_breakdown re-validates authoritatively' and the Chinese line advising to run it before compiling to save a failed round trip), plus what to do with results (normalized_patch vs errors, retry_feedback to feed back to the model). Nothing is left to inference.

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