find_shots

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

With no annotations, the description carries the full behavioral burden and does so thoroughly: it discloses the local SigLIP 2 engine, proxy-frame comparison, ranked in/out results with scores, marker creation and replacement, optional sequence creation, and first-search versus later-search latency. It also explains the project-clip/proxy scope like describe_sources.

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 front-loaded with the core purpose and examples, then proceeds logically through engine behavior, side effects, optional timeline output, source scope, and latency. Despite being a dense paragraph, every sentence contributes useful information for invoking 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 8-parameter tool with no annotations and no output schema, the description is complete enough: it explains the result shape, side effects, proxy requirements, latency profile, and optional timeline behavior. An agent has what it needs to decide when and how to call it.

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 100%, so the baseline is 3, but the description adds meaningful semantics for several parameters: markers replace prior markers on repeat searches, placeOnTimeline creates a sequence named 'Tìm: <query>' in rank order, and sourceFolder search behavior explains the first-search image-reading latency. It does not elaborate on top, bin, or waitSeconds, keeping it below a 5.

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 opening sentence states a specific verb and resource: 'Find shots by what is in the picture,' and gives concrete English and Vietnamese examples. It clearly frames the tool as content-based visual search rather than a filename or metadata lookup, and it references the sibling describe_sources for proxy behavior.

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 clear usage context through examples and explains the optional placeOnTimeline outcome. It does not explicitly name alternatives such as search_project_items or find_project_item_by_name, nor does it state when not to use this tool, so it falls short of full routing guidance.

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