generate_policy

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the read-only nature ('the compiled policy is NOT applied'), lists the return fields (policy, warnings, cost, tokens, latency), and points to the separate enforcement call. This goes well beyond minimal and fully informs the agent of side effects and results.

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 two sentences, front-loaded with the core purpose, and every clause earns its place. It packs in the action, output, read-only caveat, and the next-step endpoint without any wasted words.

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 single-parameter compile tool with no output schema or annotations, the description is remarkably complete. It covers what it does, what it returns, that it's non-mutating, and how to actually enforce the result. No important aspect is left undisclosed.

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 only type and length constraints for the sole parameter 'intent', with 0% descriptive coverage. The description compensates fully by explaining what 'intent' means (natural-language RBAC intent) and giving concrete examples, making the parameter's semantics clear.

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 a specific verb ('Compile') and resource ('natural-language RBAC intent' into 'Sytadel PolicySet JSON'). This uniquely distinguishes it from sibling tools like query_session_anomalies or run_access_review, which serve wholly different purposes.

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 clear context for use: compile intent into policy but not enforce it. It explicitly names the separate call (PUT /policies/:tenantId) needed to apply the policy, effectively explaining when to use this tool versus the enforcement step. However, it doesn't explicitly contrast with sibling tools, though those are unrelated.

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