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

The description is otherwise exceptionally rich - it discloses the admin-only authorization requirement, confirmation gating in chat, the refusal symptoms that motivate the call, the owner/admin exclusion, and the stand-down path that drops the principal to viewer without deleting the audit trail. However, it states that provisioning an organisation that already holds a live board identity is 'a no-op that reports the existing grant unchanged', which is idempotent behavior and directly conflicts with the idempotentHint=false annotation. Because the description contradicts the structured hints, the dimension is penalized despite the quality of the surrounding 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 purpose is correctly front-loaded in the first clause, but the remainder is one dense paragraph of chained clauses covering eligibility, role semantics, no-op behavior, confirmation gating, and teardown. Little of it is filler, yet the lack of any structural break makes it harder to scan than its length warrants.

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 privileged mutation with no output schema, the description covers what an agent needs: prerequisites (org admin), the refusal state that motivates the call, the effect of the role_slug argument, the no-op case, the confirmation gate, and how the grant is later removed. It even hints at the response ('reports the existing grant unchanged'). Nothing material 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 description coverage is 100% and the enum's own description already documents the default and the owner/admin refusal, so the description is mostly restating structured data. It adds a small amount of meaning ('operator' as the day-2 operations profile, custom roles being assignable only from the roles page), but not enough to materially exceed the schema baseline.

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 ('Provision the organisation's board service principal') and defines exactly what that principal is: the acting identity that platform-created agents use for AI board tickets. It is implicitly differentiated from the sibling designate_board_worker by explaining that designation is refused until this provisioning has happened, so an agent can route between the two 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?

Gives a concrete triggering condition ('agents are refused with no acting identity that can write'), the eligibility constraint ('Organisation administrators only'), and the inverse operation (stand the identity down from the portal's AI settings). It stops short of explicitly naming designate_board_worker as the follow-up tool, so the routing is inferable rather than stated.

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