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

Annotations mark destructiveHint=true and readOnlyHint=false; the description usefully explains why, disclosing that the call may delete expired drafts and that drafts expire after 7 days if unkept. It also clarifies the operation is idempotent-ish ('create or reuse') and stays inside AdsAgent rather than touching Meta ads, though permissions requirements are unstated.

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 short sentences, front-loaded with the action and output, followed by the boundary and lifecycle caveat. No filler; every sentence adds a distinct fact.

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?

With an output schema present, return-value explanation is unnecessary, and the description still covers lifecycle (reuse, 7-day expiry), side effects (possible deletion), and scope (no Meta ad changes). The only real gap is parameter-level detail for the targets array and connection_context.

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% across both parameters. The description adds a meaningful hint that 'targets' should come from targeting_search picks and that the result surfaces as interest_pack_name, but it says nothing about the targeting_type enum values or the connection_context pattern, leaving the schema to carry those alone.

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 (create or reuse) and resource (a temporary audience-targeting draft in AdsAgent), names the input source (targeting_search picks) and the returned artifact (interest_pack_name). The 'temporary draft' framing distinguishes it from the persistent-pack siblings such as interests_save_targets and interests_keep_draft.

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 clear context for when this applies (you have picks from targeting_search) and explicitly bounds what it does not do (does not create, publish, or modify Meta ads). It stops short of routing between this tool and interests_save_targets / interests_keep_draft / interests_save_fetched_pack, so the agent must infer which lifecycle step it is in.

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