decision_evaluate

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

With no annotations, the description carries full disclosure burden. It mentions returning 'matched rule outputs' but omits error handling (no match found?), side effects (audit logging?), or whether this is read-only execution versus state-modifying. Adequate but gaps remain.

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?

Three tightly constructed sentences each serving distinct purposes: capability description, return value explanation, and usage context. No redundancy or unnecessary verbosity.

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?

While concise, the description leaves gaps given the complexity of DMN evaluation: no output schema exists, the input schema is empty (contradicting the implied parameters), and error scenarios are unaddressed. Sufficient for basic identification but not comprehensive guidance.

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?

Zero parameters in schema establishes baseline of 4. The description adds crucial semantic context that the schema lacks: it mentions requiring a 'key' and 'typed input variables', hinting at dynamic parameter expectations not captured in the empty properties object.

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 provides a specific verb ('Evaluate'), resource ('deployed DMN decision table'), and mechanism ('by key with typed input variables'), clearly distinguishing this execution tool from sibling retrieval tools like decision_getByKey and decision_deploy.

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?

Provides some usage context ('Used to test decision logic through AI') but lacks explicit guidance on when to use this versus retrieving decision definitions or when evaluation might fail. No prerequisites or alternative workflows mentioned.

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