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

Annotations already cover readOnly, non-destructive, idempotent, and closed-world behavior, so the bar is lower. The description still adds real value by disclosing that the tool opens nothing and performs no navigation itself, and by noting the official API's read-only limits (with a verification date) — behavior an agent could not derive from annotations. It omits only the exact response shape, which is a minor gap.

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 core workflow is front-loaded in the first two clauses, but the closing sentence about the Platform API, SDK-as-MCP-server, API key location under Settings > Security & Access, and the 'checked 11 Oct 2026' annotation is a long tangent. It has some justification as a deterrent against trying the API first, yet it is verbose relative to the single fact it conveys.

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 no-parameter, no-output-schema tool, the description must explain what comes back and what to do next — it does both ('Returns how to do it... step by step' and the cotlet_browser_* follow-up). Nothing an agent needs to invoke it correctly is missing, though a sentence on how the returned instructions are structured would make it airtight.

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?

There are zero parameters with 100% schema coverage and additionalProperties=false, so there is nothing for the description to disambiguate. Baseline of 4 applies; no parameter meaning is missing because no parameters exist.

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?

States a specific verb and resource ('List members in the user's own PushPress account') and, importantly, immediately clarifies what the tool actually returns: step-by-step guidance (screens, buttons, fields) rather than data, and that it 'opens nothing by itself.' That clarification is essential because the name/title alone would suggest a direct data-fetch, so the description both names the action and corrects the likely misreading.

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?

Gives clear follow-up routing ('then do it with the cotlet_browser_* tools in the user's PushPress Cloud Browser') and explains why the official API isn't the path. However, it never states an explicit when-not or contrasts with the similar cotlet_app_guide sibling, so the agent must infer that this is the step-getting entry point.

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