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 substantive context — that a null request silently falls back to a bundled synthetic dataset, that supplied data requires permission, and that the flag does not constitute licence verification. The licence disclaimer is a useful disclosure of limits. It does not discuss rate limits, data sensitivity, or output characteristics beyond the metric names.

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, front-loaded with the outputs, then the default-run behavior, then the permission caveat — a logical ordering with no filler. The rights/licence clause is dense but each clause carries distinct 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 not be described, and annotations cover the safety profile. The remaining gap is the large request object, whose fields an agent must populate from schema constraints alone with no semantic hints about how participation_rate, spread_multiplier, or liquidity interact. Adequate for a first call, thin for correct parameterization.

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?

At 0% schema description coverage the description must carry the load, and it does explain the two top-level parameters: `request` (omit for the synthetic example) and `rights_confirmed` (set true for supplied data, does not verify a licence). However it says nothing about the eleven nested request fields — nav, participation_rate, spread_multiplier, liquidity, data_mode, confidence, horizon_days — which remain entirely undocumented. The schema is flat in practice (no nested-object disclosure in the description), so this is a meaningful but partial compensation rather than a full one.

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 the concrete outputs (days to liquidate, holdings by day, spread cost, liquidity-adjusted VaR), which pins down the resource precisely and separates it from siblings like risk_var_attribution or risk_exposure. It is a noun-phrase enumeration rather than a verb-led statement, so it is clear but slightly less directive than an explicit 'compute X' phrasing.

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 a concrete branch condition: omit `request` to run the shipped synthetic example, supply data otherwise and set `rights_confirmed=true`. That is real when-to-use guidance rather than implied usage. It stops short of stating when a caller should prefer a different tool or what happens if rights_confirmed is false.

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