list_decisions

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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds materially useful behavioral context: it is not separately rate-limited, results are ordered most recent first, the outcome_delta formula is explained, and the return fields plus accuracy_summary condition are disclosed. This is substantial added transparency.

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 purpose is front-loaded and every clause adds value: ordering, filtering, formula, safety/rate-limit, and return shape. The final field list is somewhat long but justified because there is no output schema. Minor density is acceptable here.

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 read-only list tool with full parameter schema coverage and strong annotations, the description covers ordering, filtering, safety, rate limiting, and the return shape. The only small gap is the relationship between the page_size input parameter and the 'limit' field mentioned in the return list, but this does not materially hinder correct invocation.

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 schema already documents all four parameters. The description restates the with_outcome_only behavior and explains outcome_delta, but it does not materially extend the meaning of page, limit, or page_size beyond what the schema provides. Baseline 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 uses a specific verb and resource ('Retrieve the Decision Memory audit trail'), states that it returns all logged decisions, and gives the sort order. It distinguishes itself from single-decision operations like get_decision through 'all logged decisions' and 'audit trail', though it does not name the sibling explicitly.

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?

It gives a clear usage condition for the with_outcome_only filter and explains the outcome_delta semantics, and it notes the tool is read-only and non-destructive. However, it does not explicitly state when to prefer this over alternatives such as get_decision or when not to use it, leaving some selection inference to the agent.

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