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

Annotations only declare the generic mutation profile (readOnly=false, destructive=false, non-idempotent, open-world), so the description carries the real burden and delivers: size ceilings per media type (20MB images, 50MB videos, 2MB decoded base64), mode precedence, and explicit failure guidance against retry loops. It does not state what happens on partial failure, whether the post must be unpublished/approved, or what the call returns.

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?

Two sentences, zero filler, and the primary action plus its draft constraint are front-loaded before the size limits and the fallback rule. Every clause carries a constraint an agent would otherwise guess at.

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 7-parameter mutation tool with a nested object and no output schema, the description covers the operational essentials: valid input modes, size ceilings, fallback rules, and retry/compression prohibitions. It stops short of describing the success response or where the resulting asset ordering lands, which an agent may want given the sibling reorder tool.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks: per-type size limits, the precedence of asset_ids/file_url over base64_data, and that base64 is image-only and fallback-only. It does not explain the relationship between the nested 'file' object and the flat file_url/filename fields, which remains ambiguous across 7 parameters.

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?

Names a specific verb and resource ('Attach media to a DRAFT') and constrains the target to a draft, which separates it from publish/schedule operations. It does not explicitly name the sibling operations it is adjacent to (detach, reorder, import_media_from_url), so an agent must infer differentiation from the name alone.

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?

States the precondition (target must be a DRAFT) and establishes a preference order across input modes: Asset IDs or a real HTTPS URL first, with Inline Base64 described as an 'optional 2MB image fallback only.' It adds a negative instruction against compressing or retrying unresolved file references, but never points to a sibling tool such as media preflight for validation of an unresolved reference.

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