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

Adds real behavioral context beyond the annotations: delivery as a push to the connected human only, no trigger permission needed, refusal in public/personal rooms, and rate-limiting. These are traits the readOnly/openWorld/idempotent hints do not convey, though the blocking semantics could be stated more explicitly.

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?

Front-loads the core purpose and pairs it with the workflow in the first sentence, with constraints in the second and a terse 'Rate-limited.' closer. Dense but largely earned; the parenthetical and clause stacking make it slightly busy.

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?

With an output schema present and full annotation coverage, the description need not explain return values. It supplies the delivery, permission, room, and rate-limit context an agent needs to call it correctly, leaving only minor gaps around expiration/blocking behavior.

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 all eight parameters (including ttl, options, data, idempotency_key) are already documented in the schema. The description adds no parameter-level detail beyond what structured fields provide, matching the 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?

States a specific verb (ask) and resource (the human / an approval) plus the asynchronous behavior (block on the answer). It distinguishes itself from siblings by naming wait_for_approval as the pairing tool and comparing itself to ask_question.

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 explains the workflow ('pair with wait_for_approval') and the room-context constraint (public and personal rooms are refused), which tells the agent when this call will fail. It stops short of an explicit when-not / alternative comparison against ask_question or get_approval.

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