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

With no annotations provided, the description carries the full disclosure burden and does so thoroughly. It explains the normalization of both directions ('customers includes companies that report THIS company as their supplier'), the default grouping and how to access raw records, and the data-quality caveat that revenue_percent is 'an ESTIMATE on every row' and present on only a minority of edges. This level of behavioral detail is exceptional.

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 dense paragraph that is fully front-loaded with the core resource and scope, then progressively adds operational details. Every sentence contributes unique information—purpose, bidirectional normalization, use cases, defaults, grouping, and data-quality caveats—with no redundancy or filler.

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?

For a tool with 8 parameters, no output schema, and no annotations, the description provides strong context: it explains the output fields (start date, open status, reporting side, revenue dependence), the query behavior, and the revenue estimate limitations. Minor gaps remain around limit behavior, listed_only, and company_id, but the description gives enough for an agent to understand the tool's role and expected response shape.

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 only 13% (only a boilerplate description for ticker), so the description must compensate. It effectively explains status and as_of for history, group_by for record-level granularity, and implicitly covers rel_type by listing the relationship categories. However, it omits semantics for limit, company_id, and listed_only, leaving those parameters underdocumented despite their presence in the schema.

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 explicitly identifies the resource as 'The SUPPLY-CHAIN GRAPH around one company' and enumerates its components (customers, suppliers, competitors, partners). It clearly distinguishes this tool from siblings like tengu_v3_supply_chain_geo_revenue and tengu_v3_supply_chain_revenue_dependence by covering the full relationship graph, including both directions and multiple relationship types. The phrase 'in one call' emphasizes the consolidated scope.

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 explicit use cases: 'map second-order exposure' and 'find the listed suppliers behind a product cycle'. It also gives parameter-based guidance, such as 'Defaults to CURRENT relationships; status=all or as_of=YYYY-MM-DD gives history' and 'group_by=record gives the underlying versions'. However, it does not explicitly name alternatives or state when not to use this tool, leaving a small gap in sibling differentiation.

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