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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds genuine context the annotations cannot: the data provenance ('sourced from the NZ Companies Register') and the key limitation that these relationships are 'not visible from NZX filings alone', which tells the agent why this tool exists rather than being derivable from filing data.

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?

Three sentences, front-loaded with the core purpose, followed by provenance, output shape, and uses. Nothing is padded, though the enumeration of return fields ('connection pairs, shared companies, connection density, most-connected director') is partly redundant against the output schema.

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 an output schema present, return values need not be described, and annotations carry the safety profile; the description supplies the domain framing and data source needed to interpret results. It stops just short of routing guidance to sibling network tools, which is the only real gap.

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 100% for the single ticker parameter (format and examples are in the schema), so the description adds no parameter meaning beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 ('Get hidden connections for an NZX company') and then defines the resource precisely: directors sharing private-company board seats with directors of other NZX issuers. That definition alone separates it from near-neighbours like get_director_network, get_company_connections, and get_network_intelligence, since the criterion for an edge is explicit.

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 offers use cases ('identifying undisclosed relationships, potential conflicts of interest, and board network analysis') but never says when to choose this over the numerous sibling network tools or when it is the wrong tool. Usage is implied by the scenario list rather than stated as routing guidance.

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