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

With no annotations provided, the description must carry the behavioral burden. It discloses the 'one edge per call' constraint and lists supported relations, but it does not clarify whether the operation is read-only, what the response shape is, or what happens when the optional 'relation' parameter is omitted. This leaves gaps in behavioral understanding.

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, front-loaded with the core action and then a concise usage trigger. The long list of relations is appropriate given the tool's purpose, and every clause contributes meaning without unnecessary fluff.

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?

The tool has a moderate complexity with an enum and one required parameter, but no output schema. The description does not describe the return format (e.g., list of related companies), pagination, or default behavior when 'relation' is omitted. It also doesn't clarify whether multiple relations can be requested in one call, leaving the agent to infer from 'one edge per call' that it cannot.

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 only 33% (only company_id is described as a path parameter, without real semantics). The description compensates by explaining the 'relation' parameter with examples and mapping to user intents, but it does not clarify the requiredness of relation or explain the limit parameter. The schema's enum already lists the same relation values, so the description's list adds moderate value.

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 uses a specific verb ('traverse') and names the resource ('a company's private-market graph'), clearly distinguishing this edge-by-edge relation tool from siblings like company_dossier or company_investors. It enumerates concrete relation types and maps them to user queries ('backs, competes, or sits on the board'), making the purpose unmistakable.

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 says explicitly 'Call this when the user asks who backs, competes with, or sits on the board of a company,' giving a clear trigger. It does not mention alternatives or exclusion cases, such as using a dedicated relation-specific tool like company_investors, so it misses the 'when-not' component.

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