List Websites

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

Beyond the readOnly/destructive annotations, the description discloses the monitoring semantics (monitoring_status, code, monitored_at), the absence of a total count in the API, and the correct interpretation of page_was_full. It also warns to read pagination_note before concluding a list is complete. These are non-obvious behavioral details that no annotation or schema could convey.

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?

Though longer than a one-liner, every sentence adds value: domain clarification, usage caveat, output fields, pagination guidance, and operation class. Information is front-loaded (purpose first) and logically ordered (usage → output → pagination). Nothing is redundant with the schema or annotations.

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 tool with no output schema, the description explains the response shape ('items plus pagination facts') and key record fields. It also covers the most important gotcha (no total count) and the intended filtering strategy. Given the tool's complexity, this description is fully sufficient for an agent to select and invoke it 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?

The input schema provides 100% coverage with detailed descriptions for all eight parameters, so the description does not need to compensate. It does mention filtering by company_id and suggests search as the best first filter, but these are either schema-mentioned or output-filtering tips rather than new parameter semantics. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 a specific action ('List websites in Hudu') and immediately clarifies that a website in Hudu is a live monitor, not a documentation page – a key domain distinction that prevents misuse. It also notes the lack of a company filter, further scoping the tool's behavior. This clearly differentiates it from sibling list tools.

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?

It explicitly states the endpoint has no company filter and gives a concrete recipe: list websites and match on company_id, or try search. It also explains when this tool is relevant ('what are we monitoring for Contoso?') and flags pagination caveats that affect completeness. This is practical, actionable guidance with alternatives.

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