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

Beyond annotations (readOnlyHint=false, idempotentHint=true, etc.), the description reveals the OAuth requirement, return of a subscription id, feed always-on behavior, and SMS verification with a 10/day cap. It does not elaborate on idempotency deduplication or failure scenarios implied by idempotentHint, but adds substantial behavioral context.

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 efficiently written, with the core purpose and return value in the first sentence, followed by type details and delivery channels. It consists of two long sentences rather than bullets, slightly hurting scannability, but every clause provides needed information.

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 a complex tool with nested objects and five subscription types, the description covers return value, auth prerequisites, three of five types with examples (the remaining two are in the schema), and delivery channels with verification caps. The lack of an output schema is partly compensated by the return statement, but error conditions and idempotency semantics are absent, preventing a perfect score.

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 coverage is 100%, so the baseline is 3, but the description adds semantic richness with concrete examples like 'items:["5.02"] = officer change' and 'topic:"fed"' that teach the meaning behind params.type values. It also explains delivery channels with formatting examples, exceeding the 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 opens with 'Create a proactive monitoring subscription to a live-data event stream,' a specific verb and resource that clearly distinguishes it from sibling tools like list_subscriptions and unsubscribe. It also lists supported subscription types and the return value, removing ambiguity.

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 that anonymous + BYO cannot persist subscriptions, which guides usage by requiring an OAuth account. It references complementary tools (recent_alerts, registry.alerts.json) for consuming the feed, but does not explicitly contrast with list_subscriptions or unsubscribe, leaving a small gap.

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