get_policy

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

The readOnlyHint annotation already tells the agent this is a safe, non-mutating call, and the description adds only the semantic framing that the rules are deterministic and purchase-gating. It says nothing about what the policy governs, whether the rules are static or refresh, or what an agent should do with a denial.

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?

A single eight-word sentence with no filler and no wasted clauses. It is well front-loaded, though its brevity comes at the cost of under-specification rather than as a result of disciplined editing.

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 no return-value description, an agent has no idea what the policy payload contains (rule names, thresholds, precedents) or how to interpret a denial. For a zero-parameter tool the call mechanics are trivial, but the response contract is entirely undocumented.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and no schema gap to compensate for. Baseline 4 applies for a parameterless tool.

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 phrase 'the deterministic rules that gate every purchase' identifies the resource (purchasing policy rules) and hints at its role, but it is a noun phrase with no verb, so an agent must infer that this tool retrieves them. It is distinguishable in domain from siblings like get_order or propose_purchase, but the purpose is never stated declaratively.

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?

There is no guidance on when to call this versus alternatives such as verify_audit_log or get_product, nor any note about prerequisites or sequencing relative to propose_purchase/place_order. The purchasing-gate role implies it matters before ordering, but that is inference, not guidance.

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