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

readOnlyHint=true is consistent with a pure retrieval tool, and the description adds real context beyond annotations: index/key requirements, model-match failure mode, and that the sole model call is text embedding. It also discloses the return shape (compact records with href usable by get_item/quicklook, plus attribution), though it doesn't mention pagination or result limits.

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?

Front-loaded with purpose and mechanism, then prerequisites, then return shape — a logical order with little waste. The heavy markup (double backticks, bold) and some redundancy around the embed database make it slightly longer than necessary.

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?

Covers purpose, prerequisites, failure mode, and hand-off to get_item/quicklook; an output schema exists so return values needn't be spelled out. The gaps are the two undescribed tuning parameters, which matter for controlling result volume and similarity threshold.

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 0%, so the description must carry parameter meaning. It does well for `query` (plain-language examples like 'ships at a berth') and `model` (must match the joint CLIP model used at index time), but `top_k` and `min_score` are never mentioned — notably that min_score is a cosine-similarity threshold, which is not inferable from the name alone.

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+resource ('find archived scenes matching a plain-language query over their imagery') and names the mechanism (text-to-scene CLIP embedding search). It explicitly contrasts with the sibling find_similar by noting the only model call here is text-to-vector, so an agent can distinguish the two without opening schemas.

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 prerequisites: the index must be built via `umbra embed build` and the query must use the same joint CLIP-family model as the index, with dimension mismatch surfaced as an error. It implies the alternative (find_similar for image queries) but never states when *not* to use it or how it compares to search_catalog for metadata filtering.

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