新增片段内分镜镜头

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

The annotations already cover safety (readOnly=false, destructive=false, idempotent=true, openWorld=true). The description adds real contract detail: it returns a full readback plus a new fingerprint, and it declares three negative behaviors — it does not auto-fill body text, does not reorder/move old shots, and does not generate media. It does not explain how the operation_id idempotency key should be chosen, which would strengthen the idempotency claim already in the 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?

One dense sentence plus a contract clause, front-loaded with preconditions, then the action, then the return and negative guarantees. Nearly every clause carries information; density comes at some cost to readability for non-Chinese readers but no padding is present.

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 format need not be explained, and the description still usefully states the readback/fingerprint. The remaining gaps — meaning of display_order, how operation_id must be managed, and what happens on fingerprint conflict — matter for a mutation with six required params and no schema documentation.

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?

With 0% schema description coverage, the description has to carry parameter meaning and only partly does: '核本项目分集片段归属' hints that project_id/episode_id/segment_id exist for ownership validation, and 'expected_sha256' is glossed as the latest storyboard fingerprint. display_order and operation_id receive no explanation at all, leaving two of six required params ambiguous.

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 and resource: add a shot under the official POST segments/{id}/shots endpoint, scoped to a project/episode/segment. It implicitly separates itself from pavo_script_delete_storyboard_shot and pavo_script_create_storyboard_segment, and explicitly rules out moving existing shots. It stops short of naming a sibling directly, so it is clear but not maximally differentiating.

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?

Use is implied by the stated preconditions (verify project/episode/segment ownership and the current storyboard fingerprint before adding). There is no explicit 'use this when…' guidance, no mention of when to prefer pavo_script_update_storyboard or pavo_script_create_storyboard_segment instead, and no stated behavior for a fingerprint mismatch.

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