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

With no annotations provided, the description carries the behavioral disclosure burden. It explains what the series contains, how the data is aggregated, the approximate length (~75 trading days), and the included metrics such as call/put volume, premium, C/P ratio, IV, net delta, and streak. It does not cover output structure or error/edge-case behavior, but it provides substantial behavioral context beyond the title.

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 two sentences with a high information-to-word ratio. It front-loads the core purpose, then details the metrics and typical length, and ends with a concrete use example. Every phrase earns its place; the parenthetical about the unusual filter is particularly valuable for disambiguation.

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?

Given there is no output schema, the description does a good job telling the agent what to expect: a daily series with specific fields and approximate duration. The schema handles parameter constraints. A full 5 would require a bit more clarity on the exact response shape or behavior when date_from/date_to vs the default ~75 trading days interact, but the current definition is sufficient for correct selection and invocation.

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%, so the baseline is 3. The description does not add parameter-level meaning beyond the schema, but it reinforces that the data is per-symbol and time-series based, which aligns with the symbol, date_from, date_to, and limit parameters. No parameter details are missing enough to require extra compensation.

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 names a specific resource ('one symbol's UNUSUAL options flow') and a precise operation ('End-of-day series'), and clearly distinguishes itself by noting it is aggregated from contracts that passed the unusual filter, not the full tape. This makes it easy to tell apart from siblings like get_symbol_flow and get_unusual_activity.

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 clear use context: it powers back-tests and questions like 'how has unusual flow on NVDA developed?'. It also implies a boundary by saying it is 'not the full tape', which steers an agent away from using it when raw/full tape data is requested. It does not explicitly name alternative tools, so it misses the top-level exclusion guidance.

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