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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds that execution is synchronous, task support is forbidden, and the returned JSON is internal application state for orchestration. This supplements the annotations, but it doesn't cover pagination, filtering behavior, or response structure beyond what the schema indicates.

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 with 'list campaigns,' but it mixes tool semantics with a block of response-handling instructions. Some content is redundant (e.g., repeating 'list campaigns' followed by a classification), though each sentence carries useful guidance for the agent's interaction.

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?

Despite having an output schema and a high number of optional parameters, the description omits parameter semantics and filter behavior. The tool's operational completeness relies entirely on parameter names, which are insufficient for effective use. The description focuses on output presentation rather than tool behavior, leaving significant gaps.

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%, and the description does not explain any of the 9 parameters. All parameters are optional and lack descriptions in the schema, so the agent has no semantic guidance on what 'limit,' 'cursor,' 'status,' etc. mean or accept. The description completely fails to compensate for the schema's lack of parameter documentation.

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 'list campaigns,' a clear verb+resource pair that matches the tool name and differentiates from sibling tools like get_campaign (singular retrieval) and list_advertisers (different resource). However, it doesn't elaborate on the scope of campaigns returned, making it clear but minimal.

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 provides only output-handling instructions ('Use assistantSummary first,' 'Never display raw JSON') and no guidance on when to use this tool versus alternatives. No exclusions, alternative tools, or selection criteria are mentioned.

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