create_subscription

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it discloses almost nothing beyond the core action. It does not mention that subscriptions expire, that notification_url must be a publicly reachable HTTPS endpoint, that this creates a persistent resource requiring later reauthorization, or what a successful call returns. The only added context is the resource path format.

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 two sentences are tight, front-loaded with the core action, and the resource examples earn their place. However, the brevity is a symptom of under-specification rather than efficient coverage: at 0% schema coverage, the description is short because it omits content that an agent needs, not because it has distilled everything essential.

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?

For a create operation with no output schema and no annotations, the description should explain what a successful call yields and what constraints apply to inputs like notification_url and expiration_datetime. None of that is present. While the string-only parameters keep complexity low, the missing return-value and lifecycle information leaves the definition materially incomplete for an agent that must subsequently manage or renew the subscription.

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 0%, so the description must compensate for all five parameters, but it only adds meaning for one (resource, via examples). notification_url, change_type, client_state, and expiration_datetime are left semantically bare — the agent gets no guidance on allowed change_type values, expiration_datetime format, or the purpose of client_state, all of which the schema also fails to describe.

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 states a specific verb and resource ('Create a webhook subscription') and gives concrete resource path examples ('me/messages', 'me/events', 'me/drive/root') that anchor the agent's understanding. The 'create' action clearly differentiates it from its direct siblings list_subscriptions, reauthorize_subscription, and delete_subscription, though it never names them. A 5 would require explicit sibling differentiation, but the verb alone carries most of the weight here.

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 implies the tool is for setting up new webhook subscriptions but provides no explicit when-to-use vs. when-not-to-use guidance. It does not direct the agent to reauthorize_subscription for renewing expiring subscriptions or list_subscriptions for inspecting existing ones. The parenthetical resource examples hint at valid input but are not usage guidance.

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