list_dfw_exclusions

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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false) are greatly extended with critical behavioral detail: the return envelope shape, the members_error trap ('not an empty group, so do not read it as one'), the 'scope' variant semantics ('system exclusions are NOT in the answer' under user), and that an empty list is not proof of absence — reinforcing openWorldHint. No contradiction with annotations.

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 every sentence earns its place: purpose first, then invocation trigger, datapath semantics, return shape, scope caveat, and pagination. There is no filler, and the most correctness-critical warnings (members_error, scope variant, empty-list semantics) are front-loaded before the pagination details.

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?

With no output schema and 0 required params, the description carries the entire burden of explaining outputs — and it does: envelope, per-row fields, members_error semantics, scope behavior, and pagination. An agent has everything needed to call the tool correctly and interpret results correctly, including edge cases that could otherwise cause false conclusions about VM protection.

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 100%, so the baseline is 3, and the description adds genuine value: the pagination termination condition ('stop when it is null') and the practical ceiling 'at most 100 groups,' which prevents an agent from over-fetching via limit on a list that never exceeds 100. While the schema already documents next_offset→offset, the description contributes the stop condition and expected page count.

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 '[READ] List the DFW exclusion list — the members no distributed-firewall rule reaches,' a specific verb+resource+scope that instantly distinguishes this from the sibling policy, rule, and group listers. The resource is unambiguous and the semantic definition of an exclusion is stated in one clear clause.

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 explicitly directs the agent: 'Read this before answering any question about a VM being micro-segmented or protected by DFW policy,' an unambiguous when-to-use trigger. It further clarifies that rules, groups, and policies still exist but 'none of them apply,' informing correct interpretation, though it stops short of naming a specific alternative tool or a when-not-to-use condition.

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