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

With no annotations, the description carries the full burden and does disclose a genuinely useful edge case: 'IRR returns null for degenerate cash flows (e.g. no inflows yet).' However it omits other behavioral facts an agent would want, such as confirming this is a read-only computation and whether it depends on existing transactions/events.

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?

Front-loads the concrete metric list, follows with the IRR caveat, and closes with the parameter hint. Every sentence contributes; the acronym expansions (TVPI, DPI, NAV) add clarity without bloat.

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 compensates well by enumerating the exact return fields and flagging the IRR null case. It is slightly incomplete on usage context (when this beats fetching the deal directly), but otherwise sufficient for a two-parameter read tool.

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 100%, so both parameters are already documented in the schema, including defaults and patterns. The description restates asOfDate's format and only adds a 'defaults to today' style hint, so baseline 3 is appropriate.

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 verb ('Compute aggregated metrics') and resource ('a venture deal'), then enumerates the exact outputs (cost basis, NAV, distributions, P&L, TVPI, DPI, IRR). This clearly differentiates it from the sibling get_venture_deal, which would return the raw deal record rather than derived metrics.

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 implied by the purpose and the asOfDate hint ('Pass asOfDate ... to compute metrics as of a specific date'), but there is no explicit when-to-use guidance or routing against siblings like get_venture_deal or get_venture_event. The agent must infer that this tool supersedes the plain getter when metrics are wanted.

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