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

Annotations already declare read-only, non-destructive, non-open-world behavior, and the description reinforces this with "opens nothing by itself" plus a concrete account of the return value (screens, buttons, fields). The line "Anaplan's official API: Yes" adds no usable behavior information and slightly muddies the otherwise clean disclosure.

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 disclosure is front-loaded reasonably, but the description spends words on target audiences ("from ChatGPT, Claude or any AI agent") and ends with the opaque fragment "Anaplan's official API: Yes", which reads as noise. The most important fact — that the tool only returns instructions — could have led the description instead of following the claim to set a role.

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?

With no parameters, no output schema, and rich annotations, the description covers the essentials of return format and follow-up workflow. It leaves open how the instructions are tailored (tenant role vs. workspace role, admin requirements) and whether any precondition must hold before calling, which matters for a role-change task.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description does not need to compensate for any schema gaps here.

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 names a specific verb and resource ("Set user role in the user's own Anaplan account") and, crucially, clarifies that the tool does not perform the change itself but returns step-by-step instructions. That correction is what separates it from a true mutator like anaplan_add_user, though the opening sentence alone would mislead an agent expecting to apply a change.

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?

Usage context is implied clearly: this returns guidance, then the agent executes with cotlet_browser_* tools in the user's Cloud Browser, and scope is limited to the user's own account. However, no alternative is named and no exclusions are given (e.g., when to use anaplan_add_user or a browser tool directly).

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