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

Annotations already cover read-only, idempotent, non-destructive behavior, and the description adds substantive caveats beyond them: amended-vintage data, inclusion of misses, non-validated backtest status, and the fact that this is not an individual-bank verdict. It also names the intended reporting components: watchlist, recall, uncertainty, and lead times.

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?

Three front-loaded sentences with no filler: the core read operation comes first, followed by critical caveats and the expected reporting frame. Dense domain jargon is present, but it is appropriately sized for a specialized diagnostic tool.

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 does a good job naming the key output concepts: quarterly top-decile watchlist, recall, uncertainty, and lead times. It still leaves 'named replays' and the exact return structure somewhat underspecified, so it is strong but not fully complete.

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?

There is one optional boolean parameter, and the schema fully documents it, including its default and the large-payload warning for trajectories. The description adds no additional parameter-specific guidance, so the high schema coverage justifies the baseline 3.

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: 'Read US bank current-amended-vintage diagnostics and named replays, including misses.' It distinguishes itself from geographic siblings like evidence_europe/evidence_india and from individual-bank tools by explicitly saying it is 'not an individual-bank verdict.'

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 clear when-not guidance: 'Not a validated point-in-time backtest' and 'it is not an individual-bank verdict.' However, it does not explicitly route the agent to an alternative sibling tool when those conditions matter, so it falls short of full when/when-not/alternatives guidance.

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