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

With no annotations, the description must disclose behavioral traits itself. It does so effectively by explaining idempotency ('calling twice returns the same watch rather than billing twice'), pricing model ('charged only when it actually runs'), and the free provisioning aspect. It does not cover cancellation or error handling, but the key user-facing behaviors are transparent.

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 compact and well-structured: the first sentence states the core purpose, the second adds key behavioral details, and the example provides concrete usage. Every sentence contributes value without redundancy, making it appropriately sized and front-loaded.

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 that an output schema exists, return-value details are not needed. The description covers the essential provisioning behavior, pricing, and idempotency, and it mentions the related feed tool. However, it does not explain how to stop monitoring, whether interval_seconds is in seconds, or any rate limits, which would improve completeness for a tool in a large sibling set.

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. The example clarifies that 'url' is the endpoint to monitor and 'api_key' is likely an authentication credential, but 'interval_seconds' is never explained beyond the vague reference to 'recheck cycle.' This leaves the default unit and range unclear, which is a notable gap for a required-schema field.

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's function with a specific verb+resource: 'Self-provision CONTINUOUS monitoring of an endpoint.' It also differentiates from siblings by explicitly mentioning 'guild_watch_feed' for reading change feeds, implying this tool is for setting up the watch itself, not consuming its output.

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 context on when to use this tool ('No onboarding, no human, no sales call') and hints at alternatives by directing to 'guild_watch_feed' for reading the change feed. However, it does not explicitly contrast with other sibling tools like guild_check or guild_preflight, leaving some ambiguity about when continuous monitoring is preferred over one-off checks.

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