Reject an incoming call

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the safety profile is covered structurally. The description adds real behavioral context beyond that: this act is bound to a live ringing call and to the identifiers carried by a specific webhook event, which tells the agent the operation is time-sensitive and event-driven.

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 sentences, zero filler, and the core action plus its required input source are front-loaded before the alternative branch is mentioned. Every clause 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?

A mutation tool with rich annotations and a fully documented schema, so the description need not explain return values (none exist). It covers the action, the input source, and the auto-reject alternative, though it says nothing about failure modes such as the call no longer ringing or an expired call id. That gap is minor given annotation and schema coverage.

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 every parameter (accountId, callId, from, idempotencyKey) is already documented in the schema, including the idempotency retry semantics. The description's reference to '`id` and `from`' loosely restates two of them and adds no format or constraint detail beyond the schema, 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 ('Reject a WhatsApp call ringing on the account') and pins the input to a specific source ('the `id` and `from` of its `call.received` webhook event'). No sibling tool handles call rejection, and the webhook-event framing makes the tool unambiguous.

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 the triggering condition (a call currently ringing, surfaced via a `call.received` event) and names an alternative path for a different goal: 'To reject every call automatically, set `rejectCalls` with update_account.' The agent can choose between one-off rejection and blanket auto-rejection without inference.

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