submit_director_feedback

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

No annotations are provided, so the description carries the full burden. It does disclose real behavior beyond the schema: output is localized, it will not restart or break approved blocking, and it prescribes exact F-Curve/timing values. It omits whether the submission mutates project state, whether it must follow validate_human_greenlight, or whether repeated calls are idempotent.

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 two-sentence summary is front-loaded with the core action and its key guarantee, followed by a compact args block. Given zero schema description coverage, the per-parameter lines are not padding but the only parameter documentation available, so every sentence earns its place.

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 output schema exists, so return values need not be explained. Still, for a submission tool whose output drives downstream modification work, the description leaves out state effects, sequencing relative to validate_gate/validate_human_greenlight, and the boundary with classify_error. Adequate to call correctly, not adequate to call at the right moment.

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 0% – every property carries only a split title – so the description must compensate, and it does with concrete format examples for all four parameters ('Frames 45-60', 'CHAR_Hero'/'CAM_Main'/'PROP_Door', defect and corrective-action samples). It stops short of stating constraint rules, such as whether frame_range must fall inside an approved blocking range or which subject naming conventions are valid.

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?

Names a specific verb and resource: process director feedback and produce a localized 'Surgical Modification Order' with F-Curve/timing adjustments. That is far more than a restatement of the name. However, it never distinguishes itself from the sibling classify_error, which the 'Classifies error severity' clause overlaps with, so an agent cannot tell from the description alone which one owns severity classification.

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?

There is no statement of when to call this versus alternatives, no prerequisites, and no exclusions. The phrase 'without restarting or breaking approved blocking' is a behavioral constraint on the output, not guidance on when to invoke the tool. With sibling tools like classify_error and validate_gate nearby, routing guidance is genuinely needed and absent.

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