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

With empty annotations, the description carries the full burden of behavioral disclosure. It does a good job explaining side effects like the heartbeat's dead-man's switch and the fact that it returns a ping_url and ping_email. It details that domain checks use RDAP and tls watches cert expiry, giving agents insight into the underlying behavior. However, it does not describe error conditions, rate limits, or the general return structure beyond heartbeat, which is a notable gap for a creation tool.

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 long (about 150 words) but every sentence adds value given the tool's complexity. It front-loads the core purpose ('Create a monitor') and then systematically lists kinds and options. While it could be tightened, the structure is logical and covers the necessary variety without redundancy, making it acceptable for a multi-kind creation 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 tool's complexity (7 kinds, many optional parameters) and the lack of an output schema, the description is fairly complete. It explains each kind's target, required fields, and response details for heartbeat. It even points to /llms.txt for additional fields. However, it does not describe the general creation response (e.g., monitor ID, status), error cases, or authentication requirements, which would improve completeness for an agent invoking this API.

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?

Even though schema description coverage is 100%, the description significantly enhances parameter semantics. It maps each parameter to the kinds that use it (e.g., url for http, target for tcp/tls/domain/dns, name required for heartbeat) and introduces numerous additional properties (expect, keyword, slow_ms, etc.) that are not in the schema but are valid via additionalProperties. This provides crucial meaning that the schema alone lacks, especially for choosing the right combination of parameters based on kind.

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 explicitly states 'Create a monitor' and then details the distinct kinds (http, tcp, tls, domain, dns, heartbeat) with their specific requirements, making the tool's purpose unambiguous. It clearly differentiates from sibling tools like update_monitor, delete_monitor, and check_url by focusing on creation and the monitor types it covers.

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 strong guidance on how to construct a monitor for each kind, listing required parameters and common options. It does not explicitly state when not to use this tool or name alternatives, but the specificity of the kinds and their fields makes the intended usage clear. The note that extra properties pass through encourages flexible use but doesn't explicitly exclude alternatives.

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