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

The description adds valuable behavioral context beyond the annotations: it states that execution is synchronous, task support is forbidden, and the returned JSON is internal application state. It also provides response-handling instructions (e.g., never display raw JSON, use assistantSummary first), which clarify the nature of the tool's output. No contradiction with the readOnlyHint, idempotentHint, or destructiveHint annotations.

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 padded with several sentences of generic response-formatting instructions ('Use assistantSummary first,' 'Never display raw JSON,' etc.) that could apply to any tool. These instructions distract from the core purpose, which is stated only tautologically. A concise, informative description would focus on the tool's function and parameters.

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 annotation hints, the description is functionally incomplete. It fails to explain what templates are, what the filter parameters do, or when to use this tool. The operational notes about output handling are present but do not compensate for the missing core functionality and usage 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?

The input schema has 9 optional parameters with 0% schema description coverage, and the tool description does not mention any of them. limit, cursor, seatId, status, accountId, campaignId, creativeId, and advertiserId are left completely unexplained, leaving the agent without any understanding of their meaning or how to use them for filtering and pagination.

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 begins with 'list templates,' which is a direct restatement of the tool's name and title, offering no new information about what templates are or what the tool does. It lacks any scope, differentiating details, or context that would distinguish it from sibling list tools such as list_campaigns or list_creatives.

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 gives no guidance on when to use this tool versus alternatives. It includes 'Task support: forbidden' but that is a constraint, not a usage scenario. There is no mention of use cases, prerequisites, or the kind of queries that would make list_templates the appropriate choice.

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