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

The description frames this as a pure read ('Read...', 'No credits or media generation'), while annotations declare readOnlyHint=false and destructiveHint=true. An agent gets no explanation for that gap, so it cannot tell whether the 'destructive' hint reflects a pack-level default or a real risk when calling. Beyond stating there is no credit spend or media generation, no further behavioral context (auth, session prerequisites, why a read needs a request_key) is supplied.

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 short sentences, front-loaded with the resource being read, then the downstream hash handoff, then the refresh condition. Every sentence carries information and there is no filler. The only structural weakness is that the hash sentence is the least accurate one, placing a schema-invalid instruction in a prominent position.

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?

An output schema exists, so return values need not be spelled out, and the description correctly focuses on the hash handoff instead. But for a six-parameter tool with a nested arguments object and session-bootstrap fields (work_id, read_skills, request_key, expected_catalog_version), leaving half the parameters undocumented and referencing a nonexistent expected_spec_hash leaves real gaps.

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 only 50%, so the description needs to compensate and does not: work_id, request_key, project_id and edit_variant_id are never explained. Worse, it instructs the agent to 'pass it as expected_spec_hash,' but no such property exists in the input schema, whose nested arguments object only accepts project_id and edit_variant_id with additionalProperties=false. The one parameter-level instruction in the description therefore points at a field the schema rejects.

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 and resource: 'Read the selected Film edit's saved color decisions and current clip, scene and act identities.' That is unambiguous about what data comes back. It does not, however, explicitly distinguish itself from nearby read siblings such as native.read_film_studio_project, native.read_film_three_d, or the mutating native.set_film_color_look.

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?

It gives a concrete lifecycle rule: 'Read again after an edit or selected take changes,' which tells the agent when to re-invoke rather than cache. It also chains forward into native.set_film_color_look by saying to pass the returned hash as expected_spec_hash. It stops short of naming when-not-to-use or an explicit alternative read tool.

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