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

Annotations flag destructiveHint=true, but the description adds far more: the change takes effect on the next request with no logout, unmentioned permissions are preserved, and you cannot edit the role you are signed in under. These are non-obvious side effects and constraints an agent needs before invoking.

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?

Front-loaded with the action, then routing, then constraints, so the ordering is sound. Some rhetorical padding ('PERMISSIONS ARE POWER', the cabinet metaphor, the repeated confirmation instruction) costs a little density but each paragraph still carries usable guidance.

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 destructive mutation with no output schema, the description covers effect timing, preservation of unlisted fields, self-role restriction, id sourcing, and the alternative tool. Nothing an agent needs to call it safely is missing.

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 coverage is 100%, so the baseline is 3, but the description adds real semantics: grant ids come from get_permissions, revoke ids come from the role's granted list in get_roles, and permissions not listed are left untouched. That sourcing and default-behavior detail is not in the schema.

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 precise verb+resource ('change what a role allows, or rename it') and gives concrete examples of the change ('let cashiers give discounts'). It explicitly distinguishes itself from the closest sibling by naming assign_role for per-person changes, so an agent can route correctly without opening either schema.

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?

Explicit about when to use it (role-wide permission changes), when not to (single-person changes → assign_role), and the required preconditions: confirm with the merchant, name the person and role, and never act on an inferred change. Also names the hard exclusion of editing your own signed-in role.

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