search_videos

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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses that returned video_urls are short-lived presigned URLs that expire within hours, advises to fetch immediately and not store, and explains how to get a fresh URL. It also states that results are ranked by relevance and mentions auth requirements. No contradiction with annotations.

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 purpose and usage guidance, and each paragraph adds behavioral or auth context. There is a slight redundancy between 'recommended first step' and 'instead of asking ask_video...' but overall it is tight and well-structured.

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 output schema covers return values, and the description covers URL expiration, auth, and when to use it. However, with 5 parameters and zero schema-level descriptions, the optional parameters—especially rationale—are not documented anywhere. The tool is usable for the main search path but not fully specified for a correct call using all filters.

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 compensate for missing parameter meanings, but it doesn't explain group_id, video_ids, rationale, or max_results semantics. The purpose makes 'query' obvious from context, and the schema provides defaults/types, but optional filtering parameters and 'rationale' remain unclear. This is a significant gap.

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 clearly states what the tool does: 'Find WHEN and WHERE something happens across your videos' and explains that it returns timestamped results ranked by relevance. It also distinguishes itself from ask_video by saying to use these timestamps as start/end in ask_video, so an agent can tell them apart.

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?

It explicitly positions this tool as 'the recommended first step for most questions' and tells the agent to 'search first' instead of asking ask_video about the entire video. It also explains how to chain it with ask_video by using returned timestamps as start/end, and notes permission requirements ('Requires search_only or full pipeline').

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