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

Annotations already establish readOnlyHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-recoverable context: the pricing model ('$2.00/call after free trial') and the fact that the call produces a risk register, thesis, and conditional rNPV band. It does not mention runtime, failure modes, or what a low-quality deal profile yields.

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?

A single sentence with a front-loaded arrow chain that mirrors the actual processing order, plus parentheticals for the conditional case and the price. No filler and nothing repeated from the title or annotations.

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?

For a high-complexity, paid, nested-object tool with no output schema, the description does well on deliverables and cost. However, the entire input contract for the deal profile is absent, and an agent cannot know whether a partial profile is acceptable or how scoring degrades without `indications`-type fields.

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% and the single `deal` parameter is an untyped nested object with additionalProperties=true, so the agent has no documented shape for the deal profile. The description contributes only one hint, that biotech deals carry an `indications` field. Required fields, accepted keys, and the effect of missing data are all left undocumented in both places.

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 operation (a full underwriting chain on a deal profile) and enumerates the concrete stages and artifacts produced: financial integrity, trend, industry position, stress tests, conviction score, risk register, investment thesis, and an rNPV band. That is far more specific than the title alone. It stops short of differentiating itself from the closest sibling, validate_financials, which plausibly overlaps with the 'financial integrity' stage.

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?

Usage is only implied: the agent can infer this is the deep-dive tool for scoring a deal, and the parenthetical clarifies the biotech case where `indications` is present. There is no explicit when-to-use/when-not guidance and no routing to validate_financials or company_report, which are the obvious cheaper alternatives for a subset of this work.

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