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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the trailing "Read-only." is redundant. The description does add real behavioral content by describing what the graph is composed of (nodes, edges, investor flow, co-investment pairs), but says nothing about result size, the 2000-item cap, or pagination.

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?

It is dense and front-loaded with the graph model before the alternative-tool routing, and every clause except the trailing "Read-only." carries information. That redundant sentence is the only waste, so it falls just short of perfect.

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 annotations covering safety and an output schema covering the return shape, the description only needs to convey the graph model and focusing behavior, which it does well. The gap is that the required companyId's role in scoping the network is never stated.

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 67% and the two UUID parameters are documented only as "UUID value wrapper." The description compensates for focusId by explaining it centres the graph on one node with a two-hop neighbourhood, but the required companyId and the limit parameter get no explanation at all.

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 resource concretely — a network graph with people/companies/firms as nodes and roles/investments as edges — plus the investor-flow and co-investment semantics. It is immediately distinguishable from graph-adjacent siblings like fundraising_get_paths_to_target or fundraising_get_network_stats.

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 an explicit routing rule ("For ranked warm routes to an investor use fundraising_get_paths_to_target") and explains the focusing behaviour ("Centre on one node with focus_id for its two-hop neighbourhood"). It does not address when to prefer other network siblings such as get_reachability or list_network_people, so it stops short of full when/when-not coverage.

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