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

Annotations already cover read-only, idempotent, non-destructive and open-world, so the bar is lower; the description still adds real value by disclosing prefix-aware matching, the exact fields returned per match, and that every response carries ICIJ licence attribution plus a 'not evidence of wrongdoing' caveat. Minor gaps remain around empty-result behavior and whether results are ranked or capped aside from the schema's limit.

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 core action, then example use cases, then the drill-down routing, then the return/caveat note — a sensible order with almost no filler. It is on the long side for a search tool, but each clause carries distinct information.

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 no output schema, the description compensates by naming the returned fields and the attribution/caveat that accompany every response, and it closes the loop with the follow-up tool. An agent has everything needed to call it and interpret the result.

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 100%, so the baseline is 3, but the description earns a bump by explaining the matching semantics of the name parameter ('Mossack' matches 'Mossack Fonseca'), which the schema's 'part of a name' phrasing only implies. It also reiterates node categories, though it adds nothing beyond the schema for limit and jurisdiction.

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 and resource ('Search the ICIJ Offshore Leaks Database by name') and enumerates the node kinds covered and the five source investigations. Clearly differentiated from the sibling offshore_entity, which it explicitly reserves for drill-down by node_id.

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?

Gives concrete question patterns it answers ('is [name] in the Panama Papers', 'offshore companies registered in [jurisdiction]') and an explicit hand-off rule: use offshore_entity with a node_id for full details and linked officers. The agent knows both when to call this and what to do next.

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