Acknowledge notifications

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

Adds real value beyond the annotations: it discloses the irreversibility ('this cannot be undone') and the downstream effect on future polls ('so it is not returned again'), which the destructiveHint=true annotation only implies. It does not cover idempotency or whether acking one batch affects other queued batches, so it stops short of a 5.

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, no filler. The purpose and its consequence come first, and the call precondition plus irreversibility warning follow — correctly front-loaded in priority order.

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 and annotations declare the destructive profile, so the description needn't explain returns or safety. What it supplies — purpose, ordering, irreversibility — closes most gaps; only edge-case behavior (retry after failed delivery, idempotency) is unaddressed.

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 three parameters (account_alias, receipt, context) are already documented in the schema, including the note that context is accepted verbatim from a poll. The description adds nothing parameter-specific, 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 (acknowledge/confirm) against a specific resource (a batch from get_new_notifications) and names the producing sibling, so the agent can tell it apart from get_notification_status and get_new_notifications. The stated effect ('so it is not returned again') makes the operation's outcome concrete.

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 gates invocation with 'Call only after delivery', which implies the correct predecessor tool (get_new_notifications) and an ordering constraint. It lacks a full exclusions statement (e.g., what to do if delivery failed, or whether an already-acknowledged batch can be re-sent), but the positive trigger is unambiguous.

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