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

Annotations already declare idempotentHint=true and destructiveHint=false, but the description adds real extra context: no AI quota is spent, no analysis is generated, a card caps at 30 video references, and it returns the attachment ID used for detaching. This goes beyond the structured fields, though it does not describe failure modes when the 30-item cap is hit.

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?

Front-loaded with the action, then the identifier caveat and quota/limit constraints. Four dense sentences with little waste, though the parenthetical about generate_scripts analyzing at most 3 videos is tangential to attaching and slightly dilutes focus.

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 mutation tool with annotations and no output schema, it covers the important gaps: quota behavior, the 30-reference cap, and the return value (attachment ID). The unexplained brandId parameter is the only meaningful omission.

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 carry the load. It identifies the type values (video/creator) and disambiguates referenceId (use videoId, not savedVideoId), which helps, but brandId and the relationship between contentId and card are never explained. Partial compensation for a low-coverage schema.

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 (attach) and the exact resources involved (catalog/owned video or catalog creator onto a content card). It is clearly distinguishable from the sibling detach_content_reference and list_content_references, and an agent can tell what the call accomplishes without opening the schema.

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 a concrete routing instruction: analyze selected catalog videos with analyze_catalog_video first, and clarifies this call itself does no analysis. It also warns which identifier to use (videoId from saved references, not savedVideoId). It stops short of naming sibling alternatives like add_content_source or detach_content_reference explicitly, so 4 rather than 5.

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