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

Annotations already declare the tool as read-only and idempotent, so the safety profile is covered. The description adds context about the richness of returned data (multiple amount fields, vintage, lifecycle status, counts) but does not disclose operational behaviors like pagination, default sorting, or parameter interactions. It does not contradict annotations, and the added context is useful but not extensive.

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?

The description is two sentences and reasonably concise, with the core subject front-loaded. The first sentence is a dense enumeration of data fields, which is slightly run-on but not overly verbose. It earns its length by listing what the tool returns, though a more structured list might aid readability.

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?

Given 9 parameters and no output schema, the description should explain the return shape and calling conventions more thoroughly. It does describe the data included and the main filters, but it does not mention default sorting or limit behavior, does not explain the organization_dfx_id filter, and does not differentiate from similar search tools. The description is adequate for a simple search but incomplete for optimal agent decision-making.

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?

With schema description coverage at only 22%, the description compensates by naming several filters (manager, lifecycle, vintage range, strategy, Form D sold) that map to parameters like query, lifecycle_state, min/max_vintage, strategy, and min_form_d_sold_usd. However, it omits explanation of the organization_dfx_id parameter (which has a complex format in the schema) and does not mention sort/limit semantics. The description adds meaning for the covered parameters but leaves gaps for others.

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 clearly identifies the resource (venture funds) and the specific financial data returned (target, first close, final close, etc.), and states the filtering capabilities. It distinguishes itself from firm-level tools like search_vc_firms by focusing on fund-level amounts and characteristics. However, it does not explicitly say 'return a list of funds', relying on the title and context to imply a search operation.

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 description lists filters but gives no guidance on when to use this tool versus alternatives such as search_vc_firms or search_pe_funds. There is no mention of prerequisites, exclusions, or which sibling tools are better suited for specific use cases. The filters imply usage, but the description does not direct the agent toward or away from any alternatives.

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