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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: the call is non-blocking ('without waiting'), it returns the decision time when available, and it discloses the error behavior ('Returns Approval not found for an unknown ID'). This is materially more than the safety profile the annotations provide.

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 tight sentences, front-loaded with the core action and return states, then usage, then the alternative, then the error case. No sentence is redundant against the schema or annotations.

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?

Output schema exists so return values needn't be restated, annotations cover the safety profile, and the description still supplies the non-blocking semantics, the routing to wait_for_approval, and the not-found error. An agent has everything needed to call this correctly.

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 single approval_id parameter is fully documented in the schema (its provenance from request_approval), so the schema carries the burden. The prose adds no format, syntax, or lifecycle detail about the ID beyond what structured data already states — baseline 3.

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?

Names a specific verb+resource ('Get the current state of an approval request') and enumerates the exact states returned (pending, approved, rejected, timed_out, cancelled). It also explicitly distinguishes itself from the sibling wait_for_approval, so an agent can select correctly 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 explicit when-to-use cases ('status checks', 'recover after losing track of a request') and an explicit when-not/alternative ('To block until the user decides, use wait_for_approval instead'). Nothing is left to inference.

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