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

No annotations exist, so the description must carry full weight. It explains the closed-vocabulary statuses, the tradeable boolean, and the crucial nuance that 'unknown' is a real verdict with same instruction as red. It also discloses the trustworthiness check (not merely recency) by describing the drift-job re-stamping scenario. This is thorough, field-level behavioral detail.

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 dense and front-loaded with the question and call instruction. It is longer than strictly necessary due to the detailed explanation of 'unknown' and the drift-job scenario, but every sentence adds value by clarifying non-obvious contract behavior. Well-structured with clear separation of return fields, failure policy, and trustworthiness philosophy.

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 no output schema, the description must fully define what the tool returns and how to interpret it. It enumerates the statuses, the tradeable boolean, decile_convention, and per-horizon IC. It also explains the fail-closed semantics and why 'unknown' is not a placeholder. This is complete enough for an agent to confidently call this tool and correctly handle its response without guessing.

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 tool takes zero parameters, so the schema has nothing to explain. The baseline for zero-parameter tools is 4, and there is no additional parameter semantics needed. The description focuses on output semantics, which is the correct distribution of effort.

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 immediately answers the core question: it's a pre-trade health check for the alpha signal ('is the alpha signal fit to trade'). It explicitly ties itself to actions on /top-picks and /score, and details the return values (status, tradeable boolean, IC). This distinguishes it from sibling health tools like system_health or live_ic_drift.

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?

Direct instruction to 'CALL THIS BEFORE acting on /top-picks or /score' gives a clear trigger condition. It also defines the fail-closed behavior ('treat it as an empty candidate list'), telling the agent how to branch and what to do on non-healthy statuses. This is explicit, practical guidance with actionable when-to-use.

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