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

The description states 'Create a proactive monitoring subscription... Returns the new subscription id,' which implies each call creates a distinct new subscription (non-idempotent behavior). However, the annotations declare idempotentHint=true, indicating the tool is designed to be idempotent (multiple identical calls should have the same effect). This contradiction is critical: the description's claim of returning a 'new' id directly conflicts with the annotation's idempotency hint, thereby misleading the agent about the tool's actual behavior.

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 description is well-structured and efficient. It opens with a concise one-sentence summary, then logically groups types and delivery channels with bullet-like examples. Every sentence adds value—no filler. It front-loads the main purpose and critical constraints (e.g., OAuth requirement, phone verification). The length is appropriate for the complexity of the tool.

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 non-trivial complexity (3 parameters, nested objects, multiple type variants, and no output schema), the description is remarkably complete. It covers input semantics, authentication prerequisites, delivery channel behavior (always-on feed, optional email/SMS/webhook with constraints and rate limits), and even webhook security details (HMAC signing). The return value (subscription id) is stated. No obvious gaps remain for an agent to invoke the tool correctly.

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?

Although schema coverage is 100%, the description adds substantial context beyond the schema. It explains each 'type' enum value with concrete examples (e.g., polylarket_edge with params:{topic:'fed'}) and details the 'params' object structure per type. It also enriches the 'delivery' object with constraints (phone verification, 10 SMS/day cap, webhook signing). This extra information is essential for correct invocation, far exceeding the schema's basic 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?

The description starts with 'Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id.' This clearly specifies the verb (Create) and the resource (subscription to alerts), making the purpose immediately obvious. It also lists supported types and delivery channels, further clarifying the scope. Although it doesn't explicitly distinguish from siblings like 'list_subscriptions' or 'unsubscribe', the purpose is 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?

The description provides clear context: it requires a Pipeworx OAuth account and explains that anonymous and BYO cannot persist subscriptions. It also describes when each subscription type is appropriate (e.g., 'sec_8k for 8-K filings matching ticker + item codes'). However, it does not explicitly state when to use this tool versus alternatives like 'list_subscriptions' or 'unsubscribe', though the context implies creation.

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