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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds nothing further — no data freshness, scope of the NZX graph, or computation cost for the "analysis" mode — so it only meets the minimum bar for a read-only analytical tool.

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?

Two sentences, front-loaded with purpose before the usage triggers, with no filler or repetition. The quoted example queries are verbose but earn their place as retrieval triggers; slightly trimming them would tighten it further.

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, annotations cover the safety profile, and schema coverage is 100%, so the description does not need to explain parameters or return values. It adequately covers the tool's capabilities and triggers; only sibling disambiguation is missing, which caps it below 5.

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% and the mode enum values are fully documented in the schema itself ("analysis", "shortest-path", "power-brokers", "communities"). The description's mode mentions merely parallel the schema; it adds no syntax, defaults, or interactivity rules (e.g. that from/to are only meaningful in shortest-path), so baseline 3 applies.

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?

Names a specific verb+resource ("Analyze the NZX director network") and enumerates three concrete sub-capabilities — connection paths, centrality-based power brokers, and governance communities. However, it never distinguishes itself from close siblings such as get_director_network, get_chair_network, or get_knowledge_graph_shortest_path, so an agent cannot tell from the description alone which network tool to pick.

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?

Provides explicit trigger phrasings ("how is Director A connected to Director B?", "who are the most influential directors?", "which directors form clusters?") that map well onto the mode parameter, giving the agent concrete selection signals. It stops short of naming alternatives or when NOT to use it, leaving the sibling-overlap problem unresolved.

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