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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuine behavior: the default weighting, the error on ungraded/unknown dates, and the data-model caveat that per-prediction cap_weight must not be assumed to match either book without checking inference_metadata.weighting. That caveat is partly about a neighboring data model rather than this call's own behavior, and the enumerated return fields partly duplicate the output schema, keeping it just short of a 5.

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?

Front-loaded with purpose and default in the first clause, then alternatives, then the error case; dense but organized. A sentence is partly spent on per-prediction field naming that belongs to a different tool's surface, which is slight scope creep in an otherwise tight definition.

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 an output schema present, the description need not enumerate return values, and both parameters are covered by schema descriptions plus default/pairing context. It supplies the alternative tool, the default, the failure mode, and the benchmark pairing, so nothing an agent needs to call it correctly is missing.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema: it says "cap" is not merely the default but the portfolio the ledger's verdict grades, and states the invariant that each weighting always pairs with a specific benchmark. That drives the choice of parameter value, which the schema alone does not.

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?

States a specific verb and resource ("Get a resolved book's portfolio") and immediately disambiguates the two modes it returns (market-cap-weighted vs SPY, equal-weighted vs RSP). It also names the sibling it is not (get_simulation_nav), so an agent can separate it from adjacent tools without opening either 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?

Explicitly routes usage: "Use this for one book's result, and get_simulation_nav for the running portfolio across books," and adds the failure condition "An ungraded or unknown date is an error." It also documents the default mode and the pairing invariant (equal↔RSP, cap↔SPY), leaving little to inference.

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