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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuine model context beyond that: shocks are linear, exposure count is capped at 20, and liquidation and probability modeling are explicitly out of scope — material for interpreting results.

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, front-loaded fragment sentences with no filler. It is efficient, though the telegraphic style ('Linear input shocks, 20 exposures') borders on cryptic.

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?

With no output schema, the description does name the outputs (P&L/equity, asset/venue concentration), which is helpful. But the return shape and the role of equity_usd in normalizing P&L are unstated, and no usage routing is provided for a compute tool sitting among many overlapping siblings.

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. It clarifies two key semantics: 'linear input shocks' frames price_change_pct as a shock input, and 'Symbols label scenarios' explains that asset values are labels rather than live lookups. It says nothing about equity_usd's role as the denominator, venue, cost_usd, or side.

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 operation on a specific resource: shocks applied to a portfolio, computing P&L/equity and asset/venue concentration. The phrase 'no liquidation/probability model' carves out scope against siblings like crypto_exit_check and exit_cost, though the telegraphic phrasing requires some interpretation.

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?

The negative scope statement ('No liquidation/probability model') hints at when not to use it, and '20 exposures' implies the sizing limit. But no sibling is named and no positive when-to-use condition or prerequisite is given, leaving routing largely to inference.

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