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

With no annotations, the description carries the full burden and does disclose two important traits: the operation is confirm-gated (preview unless confirmed) and requires owner-level authorization. It omits reversibility, rate limits, and return behavior, but the two disclosed traits are the ones that most affect correct invocation.

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 no filler; the mutation/confirm nature and the authorization constraint are front-loaded, and the pointer to the sibling tool comes last where it is most actionable.

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 5-parameter mutation with no annotations and no output schema, the description covers the highest-risk facts (owner-only, confirm gating, capability constraints). It leaves peripheral gaps around the plain string fields and the response shape, but nothing critical to correct invocation 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 only 20% (just the confirm parameter), so the description must compensate. It does add real meaning for 'capabilities' by naming the source of valid keys and the delegable exclusions (billing, roster, payouts, ownership), but name, description, and organizationId remain undocumented in both schema and description.

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 ('Create a custom gym role') plus its scope ('from delegable capabilities'), which clearly separates it from update_organization_custom_role, delete_organization_custom_role, and list_organization_custom_roles in the sibling list.

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 concrete preconditions: 'Owner only', and routes the agent to list_organization_custom_roles to obtain valid capability keys. It does not explicitly say when to prefer this over update_organization_custom_role, but the create-vs-modify distinction is implied strongly enough.

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