Delivery: push announcement tracking event [sandbox]

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

Annotations already indicate non-read-only, non-destructive, non-idempotent, and open world. The description adds context: appends one event without modifying history, returns empty 200, and is announcement-level. No contradictions; the description enriches the behavioral understanding.

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: first covers purpose and behavior, second adds comparison to sibling and authorization. No redundant words, efficiently front-loaded.

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?

Given the annotations and schema provide substantial detail, the description covers the key aspects: purpose, event transitions, authorization, idempotency, and relation to sibling tool. Could mention error handling or rate limits, but not essential for a sandbox tool.

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?

Input schema has 100% description coverage, so baseline is 3. The description adds value by showing the typical event order (ACCEPTANCE_DONE → RECEIVED → DELIVERED, or CANCELLED) and noting that dryRun is safe. It does not repeat schema descriptions but contextualizes parameters.

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?

The description clearly states the tool appends one tracking event for an announcement, specifies the resource (announcement), and distinguishes it from the sibling tool delivery_tracking which reports parcel-level status. It also lists the possible event progression (ACCEPTANCE_DONE → RECEIVED → DELIVERED, or CANCELLED).

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 states the tool is for sandbox simulation, only for delivery-service PARTNERS, and warns that it does not modify existing history. It contrasts with delivery_tracking and explains idempotency behavior (not idempotent; re-sending logs a duplicate).

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