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

Annotations already mark this as a destructive, idempotent, non-read-only mutation, and the description goes well beyond that by disclosing the authorization model and specific failure modes (LAST_OWNER conflict, OWNER-promote restriction). This is exactly the extra behavioral context annotations cannot carry.

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?

A single dense, front-loaded passage: purpose first, then guards, then permission. The parenthetical enum list duplicates the schema enum and is the one mildly wasteful element, but nothing else is padding.

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 two-parameter mutation with no output schema, the description covers the important unknowns: authorization, guards, and error conditions. It stops short of describing the response or whether the change takes effect immediately, leaving a small residual gap.

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 two parameters. The description re-lists the role enum (already in the schema, so no added value) and implies via 'another user' that userId identifies a target user, but gives no format guidance (opaque ID vs. email) for the required userId.

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 (Update) and resource (organization member's role) with the full value domain (OWNER/ADMIN/MANAGER/MEMBER/GUEST), which separates it from siblings like add_project_member or list_org_members that also touch membership. An agent can tell what this does without opening the 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?

Clearly states the permission scope (org.member.role.update, default ADMIN+) and the two guard conditions under which the call will fail (last-OWNER demotion, OWNER-only promotion), which is strong when-to-use context. It does not name alternatives (e.g., use list_org_members to resolve userId, add_project_member for project-level roles), so an explicit exclusion is missing.

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