Fill history

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

The description adds useful behavioral details beyond the readOnlyHint annotation: it notes that profitAndLoss is null on the opening half of a round turn and set on the closing fill, and that it defaults to the current trading day. This helps an agent interpret the returned data. However, it does not cover other aspects like pagination, ordering, or what happens when no fills exist. Since annotations already declare read-only safety, the added context is valuable but not comprehensive.

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 short (two sentences) but the first sentence is vague and poorly structured. It does not front-load the key purpose. The second sentence provides a specific behavioral detail, but overall it reads like a cryptic hint rather than a clear, organized explanation. It could be more concise and clear if it stated the purpose directly.

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?

For a tool with three parameters and no output schema, the description is insufficient. It does not mention that the tool returns a list of fill records, nor does it describe the response structure, pagination, or ordering. It also does not explain that accountId is required or how the time window is applied. The description leaves out many details an agent would need to call the tool correctly and interpret results.

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 only 33% (only accountId has a description). The description compensates slightly by stating 'Defaults to the current trading day,' which implies that startTimestamp and endTimestamp are optional and default to the current day. However, it does not clarify the time range semantics (inclusive/exclusive), timezone handling, or format expectations beyond what the schema pattern provides. It adds some meaning but not enough to fully cover the undocumented parameters.

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 says 'Fills in a time window' which is ambiguous – it could be interpreted as a verb (filling something) rather than the noun (trade fills). It does not explicitly state that the tool returns a list of trade fills (execution history) for a given account. While 'profitAndLoss' and 'halfTurn' hint at fill data, an agent would have to infer the primary function. It lacks a clear verb+resource statement like 'Returns trade fill history for an account.'

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?

No guidance is given on when to use this tool versus its siblings (e.g., search_orders, get_bars). The only contextual note is 'Defaults to the current trading day,' which describes a default behavior but not selection criteria. There is no mention of alternatives, prerequisites, or typical scenarios.

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