get_ads

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

Annotations already declare the operation read-only, idempotent, open-world, and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond those annotations: results are paginated at 100 per page, the status filter is applied client-side, and offset_id is described as a pagination cursor sourced from next_offset_id. These are useful traits not inferable from the schema or annotations alone.

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 compact and front-loaded. The core behavior is captured in two short sentences, followed by a minimal, readable args list. No filler or redundant restatement of the schema exists.

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 read-only, idempotent list operation with an output schema available, the description covers the key behaviors needed to invoke it correctly: pagination volume, the client-side status filter, and the cursor semantics. It does not over-explain return values or external constraints, which is appropriate given the annotations and output schema. Some explicit guidance on when to choose this over get_ad would improve completeness, but nothing critical is missing.

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?

The schema provides the status enum and defaults but has zero description coverage. The description's Args section compensates by explaining that offset_id is a cursor taken from next_offset_id, which is meaningful semantic guidance. It also restates the status values and adds the 'client-side' filter note, giving the agent additional context about how the parameter behaves, even though the status meaning could be expanded further.

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 uses a specific verb 'List' with the resource 'ads', immediately clarifying this is a collection operation rather than a single-item fetch. It also adds the pagination size (100 per page) and the client-side status filter behavior. It does not explicitly contrast with the sibling get_ad, but the plural 'ads' and 'List' make the purpose clear.

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 implies this tool is for retrieving a paginated list of ads, and the sibling get_ad suggests a single-ad alternative. However, there is no explicit when-to-use guidance, no mention of alternatives, and no conditions that would direct an agent away from get_ads toward another tool in the ad-management group.

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