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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds real value beyond that: it discloses the taxonomy-only scope ('never reads your account') and the meaning of the status values (same_exposure vs separate) plus the returned fields, compensating for the absent output schema.

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?

It is front-loaded (purpose, then parameters, then return shape, then worked example) and every sentence carries information, but the return-field enumeration plus the workflow example make it dense for a single-argument tool.

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 supplies the return-field list and status semantics, the input format, and a concrete end-to-end usage pattern, so an agent has everything needed to call and interpret the result.

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 coverage is 0%, so the description carries the burden and does: it states the batch limit ('up to 50') and shows accepted symbol syntax for both venues ('Hyperliquid symbols (BTC, xyz:TSLA) and brokerage tickers alike'). That explains the pattern and prefix conventions the schema only encodes opaquely.

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 specific verb and resource ('Group instruments into the exposures Gambit treats as one') and immediately scopes it against the account-reading siblings by asserting it never reads the user's account. An agent can distinguish this taxonomy-lookup tool from get_positions/get_holdings without opening a schema.

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 an explicit conditional workflow: for 'my exposure to MU across accounts', first call get_positions and get_holdings, then pass the held symbols here and sum rows sharing MU's group_id. That names the alternative tools and the exact sequence, leaving nothing to inference.

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