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

Goes well beyond the annotations by quantifying cost (~22 credits per minute of video on the first call, ~0.15 credits per subsequent call), latency (about a minute), the implicit indexing side effect that makes the call non-read-only, and the crucial caveat that scores are only comparable within a single search.

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?

Three sentences, front-loaded with purpose, then return shape, then cost/latency. Every sentence carries information an agent needs before calling; nothing is padding.

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?

There is no output schema, and the description compensates by describing the return payload (Asset ID, file name, source seconds, score) and the score-comparability caveat. Combined with cost and indexing behavior, an agent has everything needed to call this correctly and interpret results.

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 real meaning: it explains that results are best 5-second windows with Asset ID, file name and source seconds plus a per-video score, which clarifies what `top` counts and how the returned score relates to the window. It does not add anything for query or projectId beyond the schema.

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?

States a specific verb and resource ('Find moments in the project's videos') plus the query modality ('by what they show or sound like, in plain words') with concrete examples. An agent can tell this is semantic content search rather than object/filter search, though it does not explicitly distinguish itself from close siblings like search_video_moments or find_objects.

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?

Gives clear operating context: the first call indexes all unread videos of the project (slow, costly), later calls are cheap, and results should be drilled into with inspect_media or read_asset. It stops short of naming an exclusion or an alternative tool for cases where semantic search is the wrong choice.

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