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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the default-to-synthetic-example behavior and the caveat that rights_confirmed does not itself verify a licence. It stops short of describing validation failures, data-volume limits, or what happens with mismatched array lengths in a heavily constrained 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?

Three short sentences, front-loaded with what is computed, then the default behavior, then the permission gate. No filler. The opening is a noun phrase rather than a verb phrase, but it is still unambiguous.

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?

The tool is complex: a deeply constrained nested request that must satisfy cross-field consistency, though an output schema exists so return values need not be explained. The description covers invocation defaults and licensing gating but leaves an agent unable to construct a valid request without reading the raw schema. Adequate but incomplete for the complexity.

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% and the request object is a large nested structure with ~11 required fields (nav, as_of, positions, returns, factors, factor_returns, data_mode, horizon_days, etc.), none documented anywhere. The description adds real meaning only for rights_confirmed and the null-request default; it says nothing about the units, alignment, or expectations of the core data arrays. With this much undocumented surface, the description does not compensate for the coverage gap.

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 concrete outputs – factor betas plus the systematic/idiosyncratic split of portfolio variance – so an agent knows exactly what analysis this produces. It does not name or contrast with any sibling (risk_exposure, risk_es_attribution, etc.), so the agent must infer differentiation from the outputs alone.

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 two explicit operating modes: omit the request to run the shipped synthetic example, or supply data with rights_confirmed=true. The permission prerequisite is stated clearly. What's missing is any routing guidance against the many sibling risk tools, and no indication of when user-licensed data is required versus optional (the data_mode enum is unexplained).

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