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

Annotations already declare readOnlyHint=true, destructiveHint=false, so the agent knows this is safe. The description adds value by noting this retrieves metadata (not video bytes), mentions specific return fields, and discloses bulk/idempotent execution behavior. The description is consistent 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?

Extremely concise: two sentences, each providing essential information. First sentence explains the core function, second explains bulk execution behavior. No wasted words.

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 read-only metadata retrieval tool with no output schema, the description covers the key aspects: what it returns, the operational nuance (downloads metadata, not content), and bulk support. Minor gaps exist: no explanation of 'cgeo' parameter semantics or format of the id/ids relationship.

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%, meaning none of the three parameters have schema-level descriptions. The description only references 'ids' for bulk support, leaving 'id' and 'cgeo' unexplained. However, 'id' is inferable from the tool name and 'bulk support' context. The description partially compensates but doesn't fully close the 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 says 'Stream/download metadata for a video' which gives a clear verb+resource action and includes the types of data returned. However, the tool name 'youtube_download' is a bit misleading since the description states it's actually metadata/stream info and not actual content download, and this distinction from sibling tools like 'youtube_api' could be clearer.

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 tool returns metadata (formats, URLs, status) rather than downloading actual video content, which is critical guidance. However, there is no explicit distinction between this and similar sibling tools, nor when to choose alternatives. The line 'Bulk support: accepts ids for batched execution' gives some usage context but no explicit when/when-not guidance.

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