real_time_video_search

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It only restates the search purpose and gives a usage hint, but does not mention what the operation returns (e.g., video metadata, URLs, result counts), possible rate limits, or any read-only implication. The agent is left without insight into the response structure or side effects.

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 short and front-loaded with the primary purpose. The operations list is a bit redundant ('search' and 'Search'), but the when-to-use note is valuable and space-efficient. No wasted words, though it could be more informative without bloat.

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 tool has no output schema and only a generic args schema, so the description must compensate by explaining both invocation and expected results. It adequately explains how to invoke the 'search' operation and when to use it, but it does not describe the return payload (titles, URLs, etc.), which is critical for an agent to assess whether the tool answers the user's query. Overall adequate but with a clear gap.

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?

The schema itself has a generic 'args' object with additionalProperties, so the tool description is the only source that names the required parameter 'query' for the search operation. It adds minimal meaning ('required: query') but does not elaborate on what the query should contain, formatting, or supported values. Baseline 3 applies because the description does provide some crucial parameter information beyond the schema, but lacks depth.

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 a specific action: 'Search videos across YouTube, Vimeo, TikTok and the web for a query.' It identifies the resource (videos), the platforms, and the query input, and implicitly differentiates from sibling video tools like realtime_shorts_search by mentioning the short-form alternative.

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?

Explicit usage guidance is provided: 'When to use: Use for full-length videos. For short-form clips use realtime_shorts_search.' This tells the agent when to select this tool and names the direct alternative, which is exactly what the dimension asks for.

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