search_transcript

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

Annotations only supply readOnlyHint=false and openWorldHint=true, so the description carries most of the weight and delivers genuinely useful traits: results are transcript lines with timestamps, each carries a deep link of the form https://youtu.be/ID?t=SECONDS, matching is case-insensitive keyword matching, and results are ranked best-match-first. What it omits is any result-count limit or pagination behavior, which matters for an open-world search.

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?

Three short sentences, front-loaded with the purpose before the return format and matching semantics; the inline deep-link example earns its space because it defines the timestamp format. Minor looseness in the colloquial opener ("talks about something") but no padding overall.

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?

There is no output schema, and the description correctly compensates by describing the shape of results (lines, timestamps, deep links) and the ranking order. Against a two-parameter search tool, the only substantive gaps are the accepted url format and any cap on returned matches.

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% and both parameters are required and undocumented, so the description must compensate. It partially does: "keyword matching" clarifies that query is literal keywords rather than natural-language semantics, and "a video" frames url as a video reference. It never states whether url must be a full YouTube URL or a bare video ID, leaving a real ambiguity in the required parameter.

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?

"Find where a video talks about something" gives a specific verb (find/search) and resource (video transcript), and the return description (matching transcript lines with timestamps) makes clear this is a keyword search rather than a full-transcript fetch. It never names the sibling get_transcript, so the distinction is inferred from the word "matching" rather than stated.

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?

Usage is only implied: "find where a video talks about something" suggests a targeted search, which an agent would contrast with get_transcript for full retrieval, but that alternative is never mentioned. There are no exclusion conditions and no note about when keyword search will fail (e.g., paraphrased content), so the agent must infer the routing decision.

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