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

Goes well beyond the annotations: it discloses the concrete failure mode (sends return `403 sending_paused`), that already-queued emails are lost, that the request body is optional, and that a `full_access` API key is required. That is exactly the operational context the destructiveHint/idempotentHint flags cannot convey.

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?

Four short sentences, front-loaded with the action and its consequence, then auth, then endpoint reference. 'The body is optional' is mildly redundant with `required: [ref]`, but overall there is no 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 effect, error behavior, lost work, auth requirement, and the underlying endpoint/operationId. Nothing an agent needs in order 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 description coverage is 100%, so both `ref` (tenant id or external_id) and `reason` (stored as `paused_reason`, has a default) are already fully documented in the schema. The description adds little parameter-level meaning beyond noting the body is optional, so the baseline 3 applies.

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 ('Pause a tenant') and immediately defines the effect ('Stops all sending for the tenant'), which clearly separates it from update_tenant, delete_tenant, and unpause_tenant. It never names a sibling explicitly, so differentiation is implicit rather than signposted.

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?

Usage is implied by the consequence ('Stops all sending... emails already queued fail'), so an agent can infer when pausing is appropriate versus updating. There is no explicit 'use this when / use unpause_tenant to resume' routing, and no stated prerequisite beyond the API key.

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