find

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

With no annotations provided, the description carries the behavioral disclosure burden. It reveals ranking criteria, the optional local vision model dependency, the constraint that find_index never transcribes or goes online, and what result elements are reported. It falls short of clarifying side effects for find_to_timeline, which appears to create a reel, and does not mention auth or failure behavior.

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 information-dense and front-loaded with the core purpose, then systematically covers each action. The final 'Actions:' enumeration is slightly redundant after the prose has already introduced all three actions, but it is harmless and aids quick parsing.

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 description covers all three actions, their parameters, key constraints, and output hints, which is especially important given there is no output schema. Some details remain implicit, such as exact query syntax, clip_name format, and valid backend values, but the agent has enough context to invoke the tool correctly.

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?

Although the schema only defines a generic args object, the description names the action-specific arguments and their meanings, such as filepath, query, limit, visual, clip_name, captions, backend, min_source_separation, and output_path. This goes well beyond the schema's bare example and effectively compensates for the lack of per-action schema detail.

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 opens with a clear purpose, 'Natural-language shot search,' then enumerates three concrete actions with distinct resources and behaviors. Each action is described with a specific verb and expected outcome, making the tool's scope immediately understandable.

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?

The description gives strong routing guidance by explaining what each of the three actions does and when it applies, including boundaries like 'it never transcribes or goes online.' It does not explicitly compare against sibling tools such as index or transcript, but the action-level guidance is sufficient for most invocation decisions.

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