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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, covering safety and idempotency. The description adds valuable behavioral context beyond annotations: hourly evaluation after data refresh, the 24-hour rate limit, webhook delivery semantics, and the return of an alert id for later deletion. It does not mention authentication or error behavior, but the added context is substantial.

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 denser than a single sentence but each clause carries needed information: cadence, delivery, rate limit, universe semantics, return value. It is front-loaded with the primary action and remains free of filler, though the universe explanation is slightly buried at the end.

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 mutation tool with no output schema, the description covers creation behavior, delivery, rate limits, and return value adequately. It leaves out authentication requirements or error conditions, but given annotations cover the safety profile and the schema covers most parameters, it is largely complete for an agent to invoke 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?

Schema coverage is 88%, so the schema already documents most parameters. The description still adds meaning for the universe parameter ("rwa" for tokenized treasuries default, "stablecoin" for pools with at least $10M TVL) and the symbol omission behavior (omit for all major stablecoins), which goes beyond the schema's brief field descriptions. It compensates for some gaps in the low-coverage parameters.

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 ("Creates a rule") and goes further to specify the evaluation cadence ("checked every hour after the data refresh") and the delivery mechanism (POSTs a JSON payload to an HTTPS webhook). It clearly distinguishes itself from siblings like list_alerts or delete_alert by describing alert creation and even names the delete counterpart.

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 explains the operational context: how often the rule is checked, the rate limit ("at most once per 24 hours per rule"), and the webhook targets (Slack, Discord, Zapier, custom server). It implies when to use it (crossing a threshold on deployments) but does not explicitly state when NOT to use it or list alternatives like list_alerts for viewing existing alerts.

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