video_find_moments

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

No annotations are provided, so the description carries the full behavioral burden. It hints at a mutation ('persist') and a read ('query') against a revision-bound local index, but it does not disclose side effects, required permissions, persistence behavior, or what happens when index data is created or replaced.

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 description is a single short sentence, but it is under-specified rather than concise. It omits essential purpose and usage information, so its brevity does not help the agent invoke the tool correctly.

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 an 11-parameter tool with no annotations, this description is far too thin. Although an output schema exists, the agent still lacks basic information about what the tool does, how the required project/revision parameters interact, and how the optional semantic-index parameters change behavior.

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?

The schema has 11 parameters with 0% description coverage, and the description does not explain any of them. Key parameters such as text, embedding, index_digest, min_confidence, selected_span_ids, and semantic_artifact are left completely undefined for the agent.

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 says the tool can 'persist or query a revision-bound local semantic index,' but it never states that it finds video moments. The name suggests moment retrieval, while the text describes index persistence/query, and it does not distinguish this tool from siblings like video_semantic_query or video_semantic_timeline.

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 guidance on when to use this tool versus alternatives. It mentions two modes ('persist or query') but does not explain which mode is appropriate, what inputs trigger each, or when another semantic/video tool should be chosen instead.

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