Score Data

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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world behavior. The description adds genuinely useful context beyond that: decisions published from the UI use trailing-underscore input names, plain names are auto-mapped, and the result reports this via inputs_renamed. It stops short of covering error or failure behavior.

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 core purpose is front-loaded in one sentence, with the naming caveat as a short follow-up. No filler, though the parenthetical about publish_decision_flow is slightly terse and could be clearer.

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 an output schema present, return values need not be explained, and all three parameters are documented. For a non-idempotent scoring call the definition is nearly complete, missing only explicit preconditions (module must be published/active) and failure-mode hints.

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 coverage is 100%, so the baseline is 3, and the description earns an extra point by explaining how input_data variable names are handled (trailing-underscore mapping, with inputs_renamed reporting the remap) – real meaning beyond the schema's generic 'variable name-value pairs'.

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 gives a specific verb and resource ('Score data against a published model or decision') and scopes it to MAS modules, which is more than a restatement of the name. It only lightly distinguishes itself from publishing/validation siblings via the parenthetical about publish_decision_flow, so it falls short of full sibling differentiation.

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 usage context is implied – you score against an already-published model or decision – and the input-naming note hints at a precondition. However, there is no explicit when-to-use/when-not or a direct pointer to alternatives like get_mas_module_step_signature for inspecting expected inputs before scoring.

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