get_decision_trace

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says 'Retrieve' which implies a read operation, but it doesn't disclose whether this tool requires specific permissions, whether it returns sensitive chain-of-thought data, whether it logs access, or what happens when no trace_id is provided. For a tool that retrieves explainable rationale, the lack of disclosure about access control or data sensitivity is a notable gap.

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 a single sentence that front-loads the key purpose and lists the three main content types (rationale, utilities, risk assessment). It's concise and readable, though it could be slightly more structured by separating the retrieval purpose from the content types.

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 5 parameters, 0% schema coverage, no annotations, and no output schema, the description is under-specified. An agent cannot determine what each action value does, how to scope a query, or what the return format looks like. The tool appears to be a complex retrieval tool with multiple modes (latest, get, list, explain), and the description doesn't explain these modes or their relationships.

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 description coverage is 0%, so the description must compensate for the 5 parameters. It mentions 'past decisions' which maps to trace_id/goal_id, and 'candidate utilities' and 'risk assessment' which map to the tool's purpose, but it doesn't explain the meaning of the 'action' enum (latest, get, list, explain), the 'limit' parameter, or how 'project' and 'goal_id' relate to trace_id. The description adds some context but leaves most parameter semantics unexplained.

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 states a specific verb ('Retrieve') and resource ('explainable step-by-step chain-of-thought rationale, candidate utilities, and risk assessment for past decisions'), which clearly distinguishes it from sibling tools like set_goal or assess_risk. It doesn't explicitly name a sibling, but the resource is specific enough that an agent can tell it apart from the other tools.

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 no guidance on when to use this tool versus alternatives. It doesn't mention that this is for past decisions only, nor does it explain when to use 'explain' vs 'list' vs 'get' actions. The sibling list includes assess_risk and query_knowledge, which could overlap, but no exclusions or routing guidance is provided.

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