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

Annotations already establish read-only, idempotent, closed-world, non-destructive behavior, so the bar is lower. The description still adds non-obvious traits: the zero-argument synthetic fallback path and the compliance semantics of rights_confirmed (an attestation, not a licence check). It does not discuss input validation failure modes, such as mismatched pnl/var lengths.

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 dense sentences, each doing distinct work: capability and test list first, the synthetic fallback second, the permission caveat third. No filler and no repetition of schema or annotation content.

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 output schema exists, so return values need no explanation, and the read-only profile is covered by annotations. However, for a tool whose payload is an eleven-field nested object, the description says nothing about data requirements — alignment of pnl and var, confidence bounds, horizon_days, or the optional ES/null-model fields — leaving a real gap for an agent building the request.

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%, so the description carries the full burden, yet it only explains top-level request optionality and the meaning of rights_confirmed. The nested BacktestRequest exposes roughly eleven undocumented fields, and cryptic ones like es_null and es_null_dof get no explanation at all, leaving only the field names to infer intent.

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?

Names a specific verb and resource ('Backtest a VaR (and optional ES) series against realised P&L') and enumerates the exact statistics produced: Kupiec, Christoffersen, Basel zone, Acerbi-Szekely Z2. That is far more precise than a generic 'run backtest', though it never distinguishes itself from the FRTB-flavoured sibling risk_frtb_backtest.

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 branching guidance: omit the request to run the shipped synthetic example, or supply data with permission and rights_confirmed=true. It also warns that setting the flag is not licence verification. No exclusions or alternatives relative to sibling tools are stated.

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