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

Annotations already declare destructiveHint=true and idempotentHint=false, yet the description adds real context: dependent-record effects must be reviewed, and approval gating differs between org-configurable MCP approvals and always-applicable business workflow approvals. It stops short of saying whether deletion fails when the role is assigned to users, which is the practical risk an agent needs.

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?

Three short sentences with the action front-loaded and the risk warning immediately after. The closing approval-policy sentence is slightly boilerplate but still short and relevant to a destructive operation.

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 an output schema and rich annotations present, the description carries less burden, and it does cover approval flow and dependency review. However, for a destructive operation the crucial behavior, what happens to users currently assigned the role and whether the call fails or cascades, is unaddressed.

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% for the single required `id` parameter, so the description must supply meaning. It never mentions that the parameter is the UUID of the custom role to delete, nor where to obtain it (e.g., from list_custom_role), leaving the only parameter undocumented in prose.

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?

"Delete custom_role" is essentially the tool name and title restated, with no additional scope or outcome detail. It does not distinguish this from sibling mutations such as update_custom_role or from what deletion actually removes (the role definition vs. its assignments).

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 only guidance is "Review dependent-record effects before confirming," a generic caution rather than a when-to-use or when-not-to-use rule. It never mentions alternatives like updating the role, reassigning users first, or checking list_custom_role / get_custom_role prior to deletion.

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