policy_decisions

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

No annotations are provided, so the full burden falls on the description. While 'View' implies a read-only operation, the description does not disclose other behavioral traits such as whether authentication is required, rate limits, or if results are real-time vs. cached. This is insufficient for a tool with no 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 two sentences long, front-loading the core function in the first sentence. The second sentence provides additional context without redundancy. Every word earns its place.

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 the tool's simplicity (2 parameters, no output schema, no nested objects), the description covers the purpose and typical usage (auditing). It could mention ordering or output format, but is largely complete for the intended use.

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?

Both parameters have 100% schema coverage with clear descriptions: 'limit' (Max decisions to return, default 10) and 'decision' (enum filter). The description adds no additional meaning beyond stating that the tool returns recent decisions, so baseline of 3 is appropriate.

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 the verb 'View', specifies the resource 'recent policy evaluation decisions', and scopes it to 'this workspace'. It also lists the possible decision types (allow/deny/escalate). This differentiates it from sibling tools like simulate_policy, which is for simulation instead of historical viewing.

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 mentions that the tool is 'useful for auditing and understanding what the policy engine has been doing,' which implies when to use it, but it does not explicitly state when not to use it or provide comparisons to alternatives like simulate_policy.

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