generate_site_config

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

Beyond annotations (readOnly, idempotent, non-destructive), the description adds critical context: it never writes to disk, never calls the API, silently drops unknown element keys, and site_id is free text not resolved against the live tenant. 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 well-structured: a front-loaded summary, then key side-effect disclosures, then concise parameter details. Every sentence adds informational value, with no fluff or redundancy.

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?

The description covers return format (structured object + YAML), side effects (none), validation target, and caller responsibilities. It omits explicit error-handling behavior on validation failure, but the presence of an output schema and rich annotations reduces the need for further detail.

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 description coverage is 100%, and the description largely restates the schema's parameter descriptions. It adds no new formatting/syntax nuances beyond what the schema already provides, though the silent-drop behavior is useful context but also present in the schema.

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 states a specific verb ('Build and validate') and resource ('one site's Prisma SD-WAN config fragment'), clearly distinguishing it from the sibling read-only/query tools. It also describes the output (structured object + YAML) and the validation target.

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 explains the tool is for offline config generation used by downstream automation (e.g., Ansible) and explicitly states it never writes to disk or calls the Prisma SASE API, leaving application to the caller. This clearly implies when to use it versus live-network tools, though it doesn't explicitly name alternatives.

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