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

Annotations already declare idempotentHint=true and destructiveHint=true; the description reinforces idempotency via 'partial update' and adds real behavior for ad_macros (appended to the Meta/TikTok ad link as ad_macros=<value>, offer URLs read {ad_macros}, empty clears it). It never explains what the destructiveHint implies — e.g., whether clearing a field is irreversible or whether changing status affects a running launch — so the most consequential behavior is left implicit.

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 sentences, no filler, and the operation type plus field list are front-loaded. The parenthetical field enumeration is dense but functional; the only minor cost is that it mixes the field inventory with the Facebook copy mapping in one long sentence.

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 12-parameter mutation with no output schema, the description covers the semantic traps (partial update, Facebook copy precedence, ad_macros clearing) that an agent could not infer. It is not fully complete: pwa_author is undocumented and nothing indicates what a successful edit returns or whether status changes propagate to live launches.

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?

With schema coverage at 58%, the description carries real weight: it explains that on Facebook, title/body/description/cta map to Headline / Primary text / Description / Call to action and are used in preference to the bundle texts, which is not in the schema. It also covers 'folder' for folder_id, but leaves pwa_author completely unaddressed in both schema and description.

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 opens with a specific verb+resource ('Edit creative metadata') and immediately narrows scope to a partial update, then enumerates the editable fields, so an agent knows exactly what the tool mutates. It also distinguishes itself from the media path by naming delete_creative_media and stating media is managed in the panel.

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?

It makes clear this is a partial update (only supplied fields change) and explicitly routes media removal to delete_creative_media, plus notes media is managed in the panel. It stops short of stating prerequisites or when to prefer create_creative over update, so it is strong but not exhaustive.

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