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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral context beyond them, notably 'Costs 1 credit on success' (billing model) and the 'public YouTube video' scope constraint that implies private/unavailable videos fail. It does not describe failure modes for videos lacking captions, so it falls just short of full transparency.

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?

Four sentences, front-loaded with the core action, then inputs, then format guidance, then cost. Every sentence carries distinct information with no redundancy.

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?

Complete enough for a read-only, open-world retrieval tool: it explains input forms, output shapes, format trade-offs, and credit cost, and needs no return-value documentation since none of the fields are hidden. It omits edge-case behavior (e.g., videos without captions) but that is a minor 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?

Schema description coverage is 100%, so a baseline of 3 applies. The description goes beyond the schema's terse 'Output format' label by explaining what each value yields (Markdown = title + text, json = timestamped segments, srt/vtt = subtitle files) and by clarifying the dual URL/ID input, adding genuine semantic value.

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?

States a specific verb and resource: 'Fetch the transcript of a public YouTube video.' The scope qualifier 'public' and the input forms (full URL or 11-character video ID) let an agent immediately distinguish this from unrelated sibling tools like get_usage and list_languages.

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?

Gives clear conditional guidance on format selection: 'Defaults to Markdown... Use json for timestamped segments, srt/vtt for subtitle files.' This tells the agent which format maps to which task. It stops short of naming an alternative tool to use instead (none exists among the siblings), so no explicit when-not is possible here.

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