decision_quality

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

With no annotations, the description carries the burden of behavioral disclosure. It explicitly states a key behavioral trait: it never looks at the outcome. It also enumerates the rubric dimensions and hints at a pairing with the decision/outcome matrix under a certain condition. The pairing statement is vague, but the core behavior is well disclosed.

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 compact at two sentences and is front-loaded with the core purpose. However, the second sentence is jargon-heavy and unclear ('Paired here with the decision/outcome matrix using today's measured alpha...'), and the first sentence is a long run-on list. It is concise but not cleanly structured.

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 single-parameter tool with no output schema, the description provides the score range, the evaluation criteria, the exclusion of outcome, and a hint at a paired matrix. What is missing is the exact return shape and the meaning of the pairing, which an agent would need to correctly interpret the response.

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 only parameter, decision_id, has no description in the schema beyond its type and title. The description partially compensates by saying 'one logged decision (see log_decision)', which implies decision_id refers to a decision created by log_decision. However, it does not explicitly state the ID format or that it is the return value from log_decision, so the guidance is incomplete.

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 that the tool evaluates process quality of one logged decision on a 0-100 scale and lists specific criteria. It references log_decision to clarify the context. However, the second sentence about being 'paired here with the decision/outcome matrix' is ambiguous and slightly muddies the core purpose, so it does not earn a 5.

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 gives useful context: it applies to one logged decision, focuses on process quality, and explicitly excludes outcome ('Never looks at the outcome'). It also mentions a condition ('when the decision is already priceable'). However, it does not explicitly name alternative tools or state when to prefer this over siblings like review_decisions, so the guidance is mostly implied rather than direct.

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