company_lookup

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

With no annotations, the description carries the full burden and does well: it discloses cost ($0.009 USDC per call), p99 latency (3000ms), the read-only lookup nature, and the mutual requirement of name/lei. It doesn't mention rate limits, auth/payment prerequisites, or pagination behavior, which keeps it out of the top tier.

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?

Front-loaded with the action and data source, then search modes, then params, then cost/latency in a compact trailing clause. Every sentence carries actionable information and there is no 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 4-parameter tool with no annotations and no output schema, the description covers what it returns, how to invoke it, and the operational cost/latency profile. The main residual gap is that payment/auth mechanics for a paid endpoint ($0.009 USDC) aren't explained, but overall it is sufficient to call the tool correctly.

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 75%, and the description adds real value on top: it states 'name or lei (one required)' — a constraint the schema does not encode since zero parameters are marked required — and documents country as ISO2 and limit as 1–20 with default 5. It adds meaning beyond the raw schema rather than merely restating it.

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?

States a specific verb (find/fetch) and resource (companies in the Global LEI Index), plus the exact fields returned (legal name, LEI, jurisdiction, register number, addresses, status, founding date). It's a highly concrete purpose, but it never names or contrasts with adjacent siblings like company_brief, company_enrich, or kyb_check, so sibling differentiation is left to the agent to infer from the 'LEI/GLEIF' framing.

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 clearly explains the two operating modes — 'Search by name (optionally filtered by country) or fetch one LEI' — with the constraint that name or lei is required, which is genuinely useful routing info. However, it offers no explicit when-not-to-use or alternative-tool guidance, so it stops short of the 5 tier.

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