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

The annotations provide destructiveHint: true and readOnlyHint: false, but the description goes beyond by explaining the soft-delete nature: 'The archived ad is preserved on the platform (it still has its id, creative_json, and history) and can be restored with unarchive_ad.' This clarifies the destructive semantics and adds context on reversibility and data preservation, which is essential for a mutation tool.

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?

The description is lengthy but well-structured with sections for purpose, usage, id retrieval, parameters, and returns. Every section adds value, especially the explicit routing away from delete_ad and the 'ALSO KNOWN AS' and 'KEYWORDS' lists. It is not overly verbose given the tool's central role as the only delete mechanism, though a slightly tighter version could be more concise.

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?

The description covers everything an agent needs: what it does, when to use it, how to obtain ids, the return format, and restoration via unarchive_ad. It also includes explicit exclusion of a non-existent delete_ad tool. The output format is shown, and given the tool's simplicity (one parameter) and presence of siblings, it is fully complete.

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?

Although schema coverage is 100% with a single parameter 'ids', the description adds meaningful detail: 'Bulk-friendly — pass several ids to archive multiple ads in a single call' and 'Array of integer ad ids (at least one).' It explains the minimum requirement and encourages bulk usage, which is not explicit in the schema beyond minItems=1.

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 clearly states the tool's purpose: 'Archive (soft-delete) one or more ads on the Metadata platform.' It differentiates from a non-existent delete_ad, emphasizing it is the only way to remove an ad, and references the restoration sibling unarchive_ad. The verb 'archive' plus the resource 'ads' and the soft-delete clarification make it unambiguous.

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 explicitly lists when to use the tool with bullet points: user asks to delete/remove/discard/trash/drop/retire/archive, wants to clean up drafts, or says 'make this ad go away.' It also warns not to hallucinate a delete_ad tool and provides steps to get ids via search_ads_by_names or get_ad_details, and mentions the alternative unarchive_ad for restoration.

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