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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description adds real value with the synthetic-example fallback and the licensing caveat ("this does not verify a licence"), which is behavior an agent could not infer from the schema. It still says nothing about cost, runtime, or what happens if rights_confirmed is omitted while a request is supplied.

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, front-loaded with the computation and regulatory reference, with no filler. The synthetic-example clause is slightly awkwardly spliced in but carries necessary information.

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 no explanation, and the description covers the two things an agent must know before calling: the data-source switch and the rights gate. The main residual gap is that the required shape of a supplied request (five-element ES cascades per risk class) is only discoverable from the schema.

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% at the top level, so the description has to carry parameter meaning and it only partly does: it explains rights_confirmed as a permission gate and explains that a null request triggers synthetic data. The nested ImccRequest fields (as_of, currency, source, data_mode, portfolio, risk_classes, base_horizon_days) get no explanation, even though data_mode's enum directly relates to the guidance given.

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 a specific computation (liquidity-adjusted, stress-scaled ES and IMCC) and ties it to a regulatory basis (MAR33), which is far more informative than the tool name alone. It doesn't name any sibling tool to contrast against, so differentiation from risk_frtb_ima_capital or risk_frtb_sbm_fx is left to the agent's inference.

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 explicit operating conditions: omit the request to run the shipped synthetic example, or supply data and set rights_confirmed=true. What is missing is any routing guidance toward alternative FRTB capital tools when the user's intent is a different calculation.

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