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

With no annotations, the description carries the full burden and does so: it discloses the token requirement, the anonymous-endpoint failure mode, the three failure reasons, the evidence-threshold caveat, the obligation to quote as-of date and n, dividend inclusion, and the need to name the scope behind any number. That is unusually complete mutation-free behavioral context.

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 WHEN / NOT for / Returns progression is well front-loaded and each block serves a distinct job. The deeply nested return-shape dump is dense and harder to scan than prose, but since no output schema exists it is doing necessary work rather than padding.

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 and no annotations, everything an agent needs is in the text: return fields, failure reasons, and the interpretive constraints around quoting results. Rule-following caveats (quote as-of and n, say which scope) close the loop on misuse.

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 4 baseline applies; there is nothing for the description to disambiguate. The prose correctly adds no parameter guidance because none is needed.

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?

Opens with a named trigger and states exactly what is returned: the forward log of grades Dantes issued live, measured alongside SPY over identical windows. It explicitly contrasts with the sibling get_dantes_rating, so an agent can distinguish the two without opening either schema.

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 WHEN block quotes real user phrasings that should select this tool, and the NOT-for block names both the exclusion condition (not a backtest, not evidence until the completed-63 count hits its threshold) and the sibling alternative for per-name grades. Nothing is left to inference.

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