vmware-nsx-security

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

No annotations are provided, so the description must carry the full burden. It documents parameter defaults but fails to disclose critical behavioral traits: whether the operation is idempotent (what happens if policy_id already exists?), what the return value contains (success boolean? policy object?), or required permissions. It mentions 'NSX Manager target name from config' implying external configuration dependency without explaining resolution behavior.

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 uses a standard Google-style Args: format that is efficiently structured. The one-line summary is followed by parameter documentation without redundant prose. Each line earns its place by conveying type constraints, valid values, or defaults.

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 this is a 7-parameter mutation operation with no output schema, the description adequately covers inputs but leaves significant gaps in operational context. It fails to describe success/failure modes, the returned data structure, or side effects (e.g., policy activation latency). The parameter coverage is complete, but the operational lifecycle is under-documented.

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 0% schema description coverage (only titles exist in the JSON schema), the description fully compensates by providing rich semantic details for all 7 parameters. It specifies format constraints (policy_id: alphanumeric/hyphens/underscores), enumerated valid values (category options), business logic (sequence_number priority ordering), and default values for optional parameters.

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 opening line 'Create a new DFW security policy' clearly states the verb (Create) and resource (DFW security policy). While 'DFW' is domain-specific jargon (Distributed Firewall), it is consistent with sibling tool names (list_dfw_policies, update_dfw_policy), making the scope identifiable. It distinguishes itself from siblings by specifying 'Create' vs 'update', 'delete', or 'get'.

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 no explicit guidance on when to use this tool versus alternatives like update_dfw_policy (e.g., 'use this only when policy_id does not exist'). It lacks prerequisites, workflow context (e.g., 'create policy before adding rules with create_dfw_rule'), or exclusion criteria.

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