RiskModels Selection vs Drift

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

Beyond the annotations (which already convey read-only, non-destructive, open-world), the description discloses the backing endpoint (POST /cohorts/pnl-decomposition), that selection+drift sum exactly to the total, that weights are held constant and not normalized, that shorts are negative weights, that unmapped positions appear in coverage.dropped, that data is historical end-of-day, and that each call costs $0.25.

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?

Dense but front-loaded: the usage condition and the primary exclusion come first, then the return/behavioral detail. Every clause carries information, though the mid-sentence semicolon chain is heavy; sizing is appropriate for a paid, non-trivial analytics call.

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?

There is no output schema, so the description must explain the return contract, and it does: selection, drift, their exact summation, and the coverage.dropped list. Together with the pricing and historical-data note, an agent has everything needed to call and interpret it.

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 the baseline is 3. The description reinforces weight-sign semantics ('a short is a negative weight') and adds the non-normalization/constant-weight constraint, but it repeats the schema's weight definition and adds little on level, end_date, min_names, or include_series.

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+resource: attributing a book's realized residual return over a date window to stock selection versus drift. It clearly distinguishes itself from the general riskmodels_decompose and from riskmodels_portfolio_exposure by naming what it does not cover, so an agent can select it without opening schemas.

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 leads with explicit 'Use when...' guidance for the target scenario and provides an explicit exclusion plus alternative: 'Not for current risk or hedges (use riskmodels_portfolio_exposure)'. When-to-use and when-not-to-use are both spelled out.

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