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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. Beyond that the description adds genuinely useful behavior: the 31-day-per-call ceiling, the implicit 24-hour default, ISO-8601 UTC time handling, and a prompt-injection warning that fields shaped {"untrusted_text": ...} are broker/hook/human data and must not be obeyed. Auth requirements and truncation behavior when limit is hit are still unstated.

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 dense sentences, no filler. The resource definition comes first, then the operating constraints, then the security caveat — correctly front-loaded so the most decision-relevant information is read first.

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 carries the burden of describing results and does so at a high level (fills, balance and commission entries), plus defaults, bounds and data-provenance handling. What is missing is whether results are truncated at the limit, how to page beyond 31 days, and the ordering of returned deals.

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 parameter names and meanings are already documented and the baseline is 3. The description adds meaning the schema does not carry: that start/end times are ISO-8601 UTC, that omitting them defaults to the last 24 hours, and that the span between them cannot exceed 31 days — a real constraint on the start_time/end_time pair.

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 the exact resource and its sub-parts: "Closed deals (fills, balance and commission entries) in a time window." This distinguishes it from sibling reads such as get_orders (working orders) and get_positions without the agent needing to open a schema, and it removes the ambiguity inherent in the generic name 'get_history'.

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?

It gives concrete operating context: default window of the last 24 hours, a hard cap of 31 days per call, and a limit range of 1..500. That tells the agent how to scope a call, but it never states when to prefer this tool over get_orders or get_audit_log, nor any exclusion such as accounts without history.

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