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

Annotation Contradiction: The annotations declare idempotentHint=true, but the description says 'Create a proactive monitoring subscription' and 'Returns the new subscription id,' implying a new resource is created each time. This contradicts the idempotency hint. Additionally, the main description omits the webhook delivery channel, which is only described in the input schema, and does not clarify idempotent behavior or failure states.

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 dense but efficient; each sentence provides meaningful details about purpose, requirements, types, and delivery. It could be slightly more concise, but the structure is logical and front-loaded with the core function.

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 complex tool with 3 params, nested objects, and multiple delivery channels, the description covers most key aspects: purpose, auth requirements, subscription types, delivery options, verification, and return value. It omits webhook support and two types from the main description, but the rich input schema fills those gaps. The idempotency conflict is a notable weakness.

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?

The input schema has 100% parameter description coverage, and the description adds valuable examples (e.g., items:["5.02"] for sec_8k, topic:"fed" for polymarket_edge, series_id:"UNRATE" for fred_series). It also explains delivery channel constraints (SMS verification, 10/day cap) that go beyond 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?

The description clearly states the tool creates a proactive monitoring subscription to a live-data event stream. It names specific subscription types and delivery channels, which distinguishes it from sibling tools like unsubscribe, list_subscriptions, and recent_alerts.

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 usage context: when to monitor an event stream, with examples for each supported type. It also contrasts with pulling alerts via recent_alerts or the registry endpoint. However, it does not explicitly mention exclusions or when to prefer alternative tools like validate_claim or deep_research.

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