Create Policy Context

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

The description says 'Create a v2 PolicyContext', a write/mutation verb, while the annotations declare readOnlyHint=true and destructiveHint=false. An agent reading the text would expect a persistent write; the annotations say the environment is untouched. The description never resolves whether the object is persisted or merely computed, and the contradiction is left for the agent to trip over.

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?

Two short sentences, front-loaded with the action and the key constraint, with no filler. It is efficient rather than padded, though the same space could have been spent resolving the read/write ambiguity instead of repeating the sunset requirement.

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 four-parameter constructor with no output schema and low schema coverage, the description should carry more weight. It discloses the mandatory sunset and the v2 dependency but leaves the readOnly-vs-create conflict, the semantics of the remaining three parameters, and the return shape entirely unexplained.

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 only 25% (valid_until is the sole documented property, and the mandatory max-180-day rule is already in the schema). The description echoes the sunset requirement but says nothing about trust_epoch, policy_version, or values_floor_version, so it does not compensate for the coverage gap on three of four 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?

States a specific verb and resource ('Create a v2 PolicyContext') and adds the material constraint that every v2 object requires one, so the purpose is unambiguous. It does not, however, distinguish this context type from adjacent constructors in the sibling list (create_agent_context, create_intent, create_charter), leaving the agent to infer the difference from the resource name alone.

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?

'Every v2 object requires one' implies the precondition for using this tool (a v2 object cannot be built without it), which is genuine usage context. There is no explicit when-not guidance (e.g. whether one context can be reused across multiple objects, or whether it must be regenerated per object) and no named alternative for earlier policy versions.

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