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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: the rationale for excluding VIDEO (generated analysis outranks terse archive records), and the fact that video rows carry a truncated preview that requires a follow-up call to get_video. This explains what the agent can expect from results without speculating.

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 four sentences, each adding distinct information: purpose, default behavior, the VIDEO exception and remedy, and the video-preview note. It is front-loaded with the core purpose and avoids filler. While slightly verbose due to the detailed explanation of the VIDEO exclusion, every sentence earns its place, and the structure is logical and scannable.

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 major aspects an agent needs to invoke the tool correctly: default kinds, how to override them, the quirk with VIDEO, and the follow-up tool for full video details. It does not mention result ranking or ordering, but that is implied by 'semantic search' and is not critical. Given the tool's moderate complexity (3 params, 1 required) and no output schema, the description is nearly complete; only minor details like result count behavior could be added.

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 description coverage is only 33%, and the description compensates partially. It explains the semantics of 'kinds' thoroughly, including the default set and how to include VIDEO. However, it does not elaborate on 'query' (beyond implying it's a natural-language text phrase) or 'limit' (though schema has a default and minimum). The description adds some meaning beyond the schema for kinds, but not for the other two parameters, so a 3 is appropriate.

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 states a specific verb and resource: 'Semantic search using embeddings' over the corpus, and explicitly differentiates it from keyword search ('finds conceptually related material that keyword search misses'). It also enumerates the default kinds (declassified documents, news, sighting archive), making its scope unambiguous and distinguishing it from sibling search tools like search_documents or search_sightings.

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 provides clear when-to-use guidance: use it when keyword search misses conceptually related material. It also explains the exact behavior of the 'kinds' parameter, why VIDEO is excluded by default, and how to include it ('Pass kinds:["VIDEO"]'). Finally, it advises routing to get_video for full details, giving the agent a complete usage path.

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