explain_decision

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

readOnlyHint already covers the safety profile, but the description adds meaningful behavioral context: which return fields to surface to the user (confidence_lookup over the raw confidence, transcript_markdown rendering) and that path_snapshot may be null. This goes beyond the annotation.

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?

Front-loaded purpose sentence followed by clearly labeled when-to-use, Args, and Returns sections makes it easy to scan. It is somewhat verbose and the decision_id format is repeated in both Args and the schema, but every section carries useful signal.

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 tool returning a complex multi-part object, the description supplies enough to invoke and interpret it, and an output schema exists as backup. Coverage of invocation, usage, and return handling is solid, though naming a sibling for the 'list decisions' case would fully close the loop.

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 100% and the schema already documents the decision_id format and example. The Args section largely restates that same '<date>/<symbol>' format, so the description adds little beyond the structured field. Baseline 3 applies.

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?

States a specific verb and resource: retrieve the full reasoning behind one committee verdict, enumerating the concrete artifacts (4-role debate transcript, CIO memo, path-probability snapshot). This clearly distinguishes it from sibling tools like decisions (list) and run_committee (execute).

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?

Gives concrete trigger phrasings ('why was today's verdict HOLD') and the audit scenario, which tells the agent exactly when to reach for it. It doesn't name a specific alternative tool or a when-not condition, so it falls short of full routing guidance.

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