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

Annotations already declare non-readOnly, non-destructive, non-idempotent, so the safety profile is covered. The description adds a genuinely useful behavioral fact beyond them: the call requires the `admin` realm role, with the ADR 0016 correction noted. It does not say what happens on a repeat submission for an already-subscribed service, which the non-idempotent hint makes relevant.

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?

Two front-loaded sentences: purpose and status first, trigger and auth note second. The ADR parenthetical is dense but earns its place as a precondition. No filler sentences.

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?

An output schema exists, so return values need not be described, and annotations cover the mutation safety profile. However, for a non-idempotent write with 0% schema coverage on three required-ish parameters, the description leaves the agent without enough to construct a correct call (what identifies the service, what tenant_id defaults to).

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% and three parameters exist, so the description must carry the load — but it only implies a 'service' value and says nothing about `service`, `tenant_id`, or `authorization` (including whether tenant_id defaults to the caller's tenant). The one genuinely helpful detail, the admin-role requirement, is auth context rather than parameter semantics.

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 ('Request a new service subscription for the caller's tenant') plus the effect ('return its status'), which is enough to separate it from read-only siblings like list_tenant_services. An agent can tell what the tool 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?

Names the trigger condition explicitly ('Call this when a tenant admin wants to add a service'), which is real routing guidance. It stops short of 5 because no alternative is named (e.g., create_self_service_tenant or list_tenant_services) and no when-not-to-use case is given.

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