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

Annotations already declare a non-read-only, non-idempotent, open-world mutation, and the description adds real value on top: the returned signing_secret, the X-AstroWay-Signature HMAC-SHA256 verification scheme, and the 10-credit cost. What is missing is the consequence of the non-idempotent hint — whether repeated calls create duplicate subscriptions — and any auth or rate-limit information.

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 core sentence and signature/cost details are front-loaded and earn their place in two tight sentences. The bracketed metadata block repeats information already implied by the title and schema (Group, Required) and adds a small amount of padding, but overall it is efficient.

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 no explanation, and the signature/secret behavior is a genuinely useful addition. However, for an open-world side-effecting subscription tool with 50% schema coverage, an agent still lacks the delivery contract points that matter most — retry behavior, URL requirements, and duplicate handling.

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?

With 50% schema description coverage, the description should carry more weight, but it adds little beyond restating that event and url are required. The event enumeration it does provide is incomplete relative to the twelve-value schema enum, which risks steering callers away from valid values, while fields and precision are left entirely to their (well-written) schema descriptions.

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?

"Subscribe to outbound webhook deliveries" gives a specific verb and resource, and the event list plus returned signing_secret make the intent unambiguous. It falls short of a 5 because it never distinguishes itself from the many per-event siblings (astroway_webhooks_dasha_change, astroway_webhooks_transit_trigger, etc.), and its three-item event list is presented as complete while the schema enum contains twelve.

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?

The description states what the tool does but gives no when-to-use guidance, no exclusion of alternatives, and no prerequisites such as whether the callback URL must be publicly reachable. Given a sibling set containing an individual tool for nearly every event type, some routing guidance was the main thing needed here.

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