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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new context: the no-argument demo fallback and the licensing caveat ('this does not verify a licence'). That caveat is important behavior an agent could not learn from annotations or schema. It does not cover output shape or computational limits, but the output schema carries those.

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, method stated first, then the two conditional paths. No filler and nothing repeated from the schema.

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?

Adequate on the licensing/gating dimension that the schema cannot express, and the output schema relieves it of explaining results. However, for a complex nested request with 0% parameter descriptions, the definition leaves an agent without guidance on the relationship between returns, assets, positions, and nav, or on data_mode 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, and it only explains the two top-level arguments. The large embedded HistoricalRequest contract (nav, as_of, assets, returns, positions, confidence, horizon_days, data_mode) is left entirely to field names and constraints, with no semantic guidance on how returns and positions relate to nav.

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 method and metric ('Historical-simulation ES') plus the attribution approach ('Euler contributions per position'), which implicitly distinguishes it from the VaR attribution sibling. It never explicitly names an alternative, so it stops short of the top band.

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 a concrete usage rule for the null-request path ('Omit the request to run the shipped synthetic example') and a prerequisite for supplied data ('require permission and set rights_confirmed=true'). It offers no guidance on when to pick this over risk_var_attribution or risk_tail, so selection between siblings is left to inference.

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