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

Annotations already carry read-only, idempotent, and non-destructive hints, so the safety profile is established. The description adds a meaningful behavioral caveat: that the Form ADV gross asset value is the reported gross assets and not fund size, commitments, or dry powder, which prevents misinterpretation of 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?

The description is a single paragraph of three sentences, front-loaded with scope and then enumerating return fields and filter criteria. It is efficient, though the field list is dense and some repetition of filter concepts exists.

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?

Whttps://annotations already cover safety, and the description explains the key return fields and their semantics, which matters because there is no output schema. It doesn't mention pagination, cursor, or default sorting, but these are standard search parameters likely implied by the schema. The description is sufficiently complete for the tool's complexity.

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?

The schema already contains descriptions for 6 of 10 parameters (60% coverage), so the description doesn't need to fully compensate. It repeats the filter list (name, manager, ADV fund type, vintage, lifecycle, minimum GAV) but provides little additional param-level semantics beyond what the schema gives. It also mentions 'manager' which isn't a defined parameter, adding slight ambiguity.

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 states a specific verb ('search'), the resource ('Funds on the private equity graph'), and the core output (amounts under their own names and bases). It lists concrete return dimensions and filter types, which distinguishes it from related siblings like search_pe_firms or search_vc_funds.

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 provides clear context that this tool targets private equity graph funds and enumerates the available filters and fields. It does not explicitly name alternatives or exclusion criteria, but the scoping is specific enough for an agent to select it over VC funds or firm search tools.

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