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

Annotations already establish that the operation is read-only and non-destructive. The description adds useful behavior context: it filters to the most relevant frame descriptions and is designed for low token usage. It does not mention any limits, ordering, or what happens when no frames match, but that is not essential for this simple read operation.

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 a single front-loaded sentence that communicates target, filtering behavior, and the token-efficiency benefit with no redundant wording. Every phrase earns its place.

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 a simple three-parameter read-only tool, the description covers the key return value (frame descriptions) and the relevance filtering, while the schema supplies parameter names and the default for top_k. It still misses explicit sibling differentiation and does not clarify how relevance results are ordered or limited, so it is adequate but not complete.

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 0%, so the description must explain parameter meaning; it only implicitly maps 'video' to video_id and 'query' to query. top_k is never mentioned in the description, leaving its semantics entirely to the schema's bare name and default.

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 names a specific resource ('frame descriptions for a video') and a specific operation ('return only ... most relevant to a query'), so the tool's core purpose is clear. It does not explicitly contrast with siblings like semantic_search_media or get_media_description, so it lacks the explicit differentiation that would earn a 5.

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 implies the use case: when you need a compact, query-relevant subset of frame descriptions from a video, with low token usage. It does not state when to prefer an alternative, nor does it name any exclusions, so guidance is only implicit.

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