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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=false, openWorldHint=true) by disclosing the 45-second wait, the delivery fallback chain, and that the approval ID survives client timeouts and reconnects. The instruction to re-poll rather than re-request implicitly conveys the non-idempotent behavior that a repeat call would open a second request.

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?

The what/how/when are front-loaded in the first two sentences, and the remaining sentences carry concrete directives rather than filler. Slightly dense with five distinct instructions packed together, but every sentence earns its place.

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 documented, and the description still usefully references the returned approval ID and pending state. For a 9-parameter tool with nested objects and a 45-second blocking wait, it covers polling, labels, and execution_context well; minor gaps remain on target_channel_slugs and appearance usage.

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 100%, so the baseline is 3, but the description adds real operating meaning: it explains when to choose action-specific approve_label/reject_label values ('Send/Cancel', 'Deploy/Hold') and when to include execution_context plus the most relevant scope. It does not address target_channel_slugs or appearance, which the schema handles alone.

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 ('Ask the ActivitySmith account owner for a decision') and immediately explains the mechanism (Live Activity, Push Notification fallback, 45-second wait). An agent can distinguish this from siblings like wait_for_approval, get_approval, and cancel_approval without opening any 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?

Explicitly routes the follow-up case: 'If the result is pending, call wait_for_approval repeatedly with the returned approval ID.' It also gives conditional guidance for labels and for including execution_context/scope when approving a concrete command. It stops short of an explicit when-not-to-use rule (e.g., when to prefer send_push_notification or cancel_approval instead).

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