List IP Addresses

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds vital non-obvious behaviors: no paging (no page/page_size), `truncated` flag for response budget cuts, no total count in the API, and the need to check `page_was_full` and `pagination_note`. It also warns that unfiltered calls can return tens of thousands of records, which is beyond annotation scope.

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 but the length is justified by the endpoint's risky default behavior. It is organized into clear paragraphs covering record definition, paging/truncation warnings, filter guidance, and return shape. The final 'Operation class: Read' is redundant with annotations and could be trimmed, but the rest is purposeful 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?

For a 10-parameter list endpoint with no output schema, the description covers all essential context: response shape (items + pagination facts), absence of total count, meaning of `page_was_full`, and `truncated` flag. It also warns about large deployments, points to related tools, and gives filter strategies. This is complete enough for safe and effective use.

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?

With 100% schema coverage, the baseline is 3, but the description adds significant practical value: it clarifies that `address` matches exact stored text and cannot find subnet hosts, recommends `network_id` as the narrowest/safest filter, provides a `fields` example to keep responses small, and links `asset_id` to hudu_list_assets. This transforms raw parameter definitions into actionable strategy.

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 'List ip addresses in Hudu' and explains what an ip_address record documents. It distinguishes itself from sibling tools like hudu_get_ip_address (single record) and hudu_list_assets (assets) by focusing on the address-centric list operation and explicitly mentioning the lack of paging.

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 gives explicit when-to-use guidance: 'Always send a filter — network_id for one subnet, company_id for one customer, address or fqdn when you are chasing a single host.' It also points to hudu_list_assets for going from an address to a machine and cautions against using `address` to find subnet hosts, recommending `network_id` instead.

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