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

Annotations already declare readOnly/idempotent/closed-world, and the description adds materially beyond them: dual execution modes, a permission prerequisite gated by rights_confirmed, and the honest caveat that the flag does not verify a licence. That licence caveat is exactly the kind of behavioral nuance structured fields cannot express.

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 tight sentences, front-loaded with what the tool computes, then mode selection, then the rights caveat. Dense semicolon phrasing is efficient rather than wasteful, though the conditional logic in the last sentence takes a second read.

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?

An output schema exists, so return values need not be described, and the description notes the desk zone (MAR32) result. For a read-only, idempotent computation with only two top-level arguments, the mode and permission semantics are covered; the remaining gap is argument-level detail, already scored separately.

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 carry parameter meaning. It explains the optionality of `request` and the role of `rights_confirmed`, but says nothing about rtpl, hpl, as_of, desk, currency, source, or the 250-element array constraint — leaving the core inputs to be inferred from field names.

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 test (FRTB P&L attribution) and the exact statistics it produces (Spearman, Kolmogorov-Smirnov) plus the output (desk zone, MAR32), which distinguishes it from the sibling risk_frtb_backtest. It stops short of naming that sibling explicitly, so an agent must infer the boundary from domain knowledge.

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 concrete mode-selection guidance: omit the request to run the shipped synthetic example, or supply data with rights_confirmed=true. This is clear when-to-use direction for both paths, though it offers no exclusion against the other FRTB siblings an agent might confuse it with.

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