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

With no annotations provided, the description must convey behavior itself. It discloses the time cadence (5-minute), the earliest available data (2020-09+), and the row limit (~100k). This suggests a read-only query operation without side effects (not explicitly stated, but implied). It does not mention authentication, rate limits, or error handling, but given the typical nature of such data extraction tools (read-only), the description is reasonably transparent. It does not contradict annotations because none exist.

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 concise, wrapping the primary purpose into the first sentence and adding operational details after the colon. It is front-loaded with the core action, but it could be better structured by separating the data contents from the range/limit info. Still, it is efficient and to the point without unnecessary filler.

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 the tool returns multiple ratio types at a specific cadence and has no output schema, the description lacks details on the shape of the response, how the ratios are computed (e.g., weighting), and clarifications on the parameters' exact usage. It covers the main data content and constraints but leaves gaps on parameter formats and return structure. More detail would make it more complete, especially with no output schema.

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?

With 0% schema coverage EB677, the description must explain what 'symbol', 'start', and 'end' mean. It only says 'Ranged pulls' hinting at a time range, but does not specify the expected format (e.g., ISO timestamps, epoch), whether start/end are required, or how symbol is used (e.g., ticker). This is insufficient for an agent to construct a correct call without additional guesswork. The description should at least indicate that start/end are optional date boundaries and symbol identifies the instrument.

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 clearly states the tool's function: retrieving positioning ratios at a specific cadence from a named archive illustrative of venue data. It distinguishes itself from siblings by listing specific metrics (top-trader long/short by accounts and size, all-accounts L/S, taker buy/sell volume) and the data source (checksummed venue archive). This makes the purpose unambiguous and differentiates it from related tools like get_open_interest or get_funding.

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 provides contextual guidance by mentioning that it supports ranged pulls and limits to ~100k rows per call. This implies the typical use case (querying historical positioning data within a time range) and sets expectations on call size. However, it does not explicitly state when to prefer this over sibling tools (e.g., when to use get_long_short vs get_open_interest). It gives clear operational constraints but lacks explicit 'use this when' or 'use that instead' guidance.

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