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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it's a safe read operation. The description adds no behavioral details beyond 'list saved templates.' It doesn't mention pagination, ordering, or scope (e.g., all templates or user-specific). With annotations covering safety, the description's contribution is neutral but minimal.

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 a single short sentence, 'List saved templates,' which is concise and front-loaded. It has no filler, but it is under-specified. It's not verbose, but it leaves out any practical usage details.

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?

Given the presence of an output schema (which may define the return format) and the simple nature of a list tool, the description is minimal but adequate for a basic read operation. However, it lacks information about pagination (cursor), how search works, or whether there's a default limit. With only 3 parameters and zero required, an agent would need to guess at semantics. The output schema might cover return structure, but it doesn't clarify parameter behavior.

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%, so the description must compensate, but it doesn't. The parameters (limit, cursor, search) are not explained in the description. However, these parameter names are self-explanatory: limit, cursor, search are common API patterns. Baseline 3 is appropriate because the schema itself lacks descriptions, and the tool description provides no additional meaning, but the parameter names are intuitive enough for a rough understanding.

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 reads 'List saved templates,' which clearly identifies the verb (list) and resource (saved templates). It is distinct from siblings like templates_get (which likely fetches a single template) and templates_create, but it doesn't explicitly differentiate from templates_list. The purpose is clear but minimal, with no elaboration on what 'saved templates' entails or how this differs from other list-like tools (e.g., creatives_list, tasks_list).

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?

There is no guidance on when to use this tool versus alternatives. The description doesn't mention any context, such as whether it's for a specific template type or when to use templates_reverse_engineer. In a suite with many sibling list tools, the lack of any usage context forces the agent to infer based on the name alone.

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