get_positions

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

Annotations already declare the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds real behavioral value beyond that: the data is live broker truth rather than cached or memory-derived, and it warns about the common unrealized-vs-realized P&L confusion. It does not cover error behavior when no broker is connected, but the annotations lower the burden and this is a minor gap.

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 compact sentences with the core truth-value and scope front-loaded before usage guidance and exclusions. The 'broker_truth / live ops' tags are slightly cryptic but efficient. No wasted words; every sentence earns its place.

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 low-complexity tool (1 param, no output schema, no nested objects), the description covers purpose, output content (flat/exposure/unrealized P&L), usage triggers, and key semantic pitfalls. The main completeness gap is the broker parameter semantics, which was already penalized under parameter semantics.

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 0%, so the description must compensate for the undocumented broker parameter — it does not. 'From a connected broker' implies the value must reference an established connection, but it never specifies the expected format, where valid values come from (e.g., get_connected_brokers), or what happens with an invalid/unconnected broker. The description leaves the sole required parameter underspecified.

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 states a precise resource ('open positions from a connected broker') with an explicit scope ('flat check, exposure, unrealized P&L only'). The 'broker_truth / live ops' tag pins down the data domain, and the explicit exclusion of realized P&L distinguishes it from tools like get_my_realized_pnl. Purpose is unambiguous.

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?

Gives concrete trigger phrases ('Use for "am I flat", "open positions", "exposure"') and explicit exclusions ('Do NOT substitute web search or memory', 'unrealized_pnl ≠ realized session P&L'). It doesn't name specific sibling tools as alternatives, but the usage boundaries it sets are strong enough to route an agent correctly.

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