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

Annotations already establish readOnly, idempotent, non-destructive and closed-world. Beyond that the description discloses ordering ('strongest first'), result-shape limits ('up to 5 source filings per relationship'), what is deliberately not included, and the critical empty-set interpretation. It stops short of any auth, rate-limit or pagination detail, but for this access pattern that is a minor omission.

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 purpose leads and the mode-specific behaviour follows, so it is front-loaded correctly. The long second sentence enumerates relationship types, which is dense but each item is load-bearing for disambiguation from sibling tools; nothing reads as 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?

An output schema exists, so return-value formatting need not be repeated, and the description still covers both invocation modes, exclusions and the empty-result interpretation. What remains unaddressed is pagination or result-size behaviour for the single-ticker mode, which is a small gap for a graph-listing tool.

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 adds real meaning the schema does not: what each parameter combination returns, the ranking of results, and the per-relationship filing cap. That is substantive semantic content beyond 'NZX ticker symbol' and 'Optional second NZX ticker'.

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 recorded connections between NZX companies') and enumerates the exact relationship types covered, each tied to its evidence source. It also carves out scope by excluding related-party transactions and fund holdings, which separates it from siblings like get_hidden_connections, get_corporate_relationships and get_entity_graph without the agent needing to open their schemas.

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 two modes are spelled out clearly: with only ticker you get the links radiating from one company, and with other_ticker you get every link between the pair. It also warns that an empty result means no recorded links rather than no real-world connection, which is a genuine usage caveat. It does not, however, name a specific alternative tool for cases where another connection view is wanted.

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