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

No annotations are provided, so the description must carry the burden. It adds a meaningful caveat: decisions are not proof of mutation, which prevents the agent from misinterpreting the data. However, it does not explicitly state that this is a read-only operation (e.g., 'This call does not modify any data'), leaving the agent to infer from the verb 'List'. The caveat is useful but not comprehensive.

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 two sentences with no redundancy. The primary purpose is front-loaded, and the caveat about evidence coverage is appended logically. Every word earns its place; it is concise and well-structured.

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 no annotations, no output schema, and 0% schema description coverage, the description should provide more context. It covers the core purpose and data semantics but omits parameter explanations, any statement about side effects (read-only vs. mutation), and return format details. For an agent to call this correctly, it would need to guess about the meaning of status values and the response shape, making the description incomplete.

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 mention the parameters 'limit' or 'status' at all. The names hint at their purpose (a count limit and a status filter), but the status enum values (open/prepared/dismissed) are unexplained, and there is no guidance on how limit behaves (e.g., default or max). The description 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 uses a specific verb 'List' and a clear resource 'tenant-owned TikTok optimization recommendations', scoped to tenant ownership. It also clarifies the nature of the data ('source snapshot and evidence coverage'), which distinguishes it from action-oriented siblings like optimization_dismiss_decision or optimization_prepare_action. The purpose is unambiguous.

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 viewing recommendations rather than acting on them, and the sibling names (dismiss, prepare, evaluate) suggest alternatives. However, it does not explicitly state when to use this vs. those tools, nor provide exclusions or conditions. The guidance is implicit rather than explicit.

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