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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral context beyond them: the data provenance (62,000+ NZX documents), the relation_type taxonomy, and the relation_confidence levels (high/medium/low), which help an agent judge result reliability.

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 is front-loaded in the first clause, and the enumeration of taxonomy values is useful rather than filler. The sentence on 'network of business relationships, competitive dynamics, and sector interconnections' is mild marketing fluff but short enough not to hurt readability.

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 and annotations covering the safety profile, the description need not explain return values, and it covers provenance, taxonomy, and filtering. The main omission is sibling differentiation, which is the one thing an agent with 150+ tools would most need.

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. The description goes beyond the schema by enumerating the full relation_type vocabulary (supplier, customer, partner, competitor, etc.), giving an agent the concrete values to pass to the 'relation' filter, and it paraphrases the direction semantics ('companies it references' vs 'companies referencing 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?

The description names a specific verb+resource ('Get peer mentions for an NZX company') and then defines the scope precisely: which companies reference it and which it references, extracted from NZX announcements. This is far clearer than a bare name, but it never distinguishes the tool from close siblings like get_company_connections, get_corporate_relationships, or get_network_intelligence.

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 explains how to filter (the 'relation' parameter) but never says when to reach for this tool over the numerous other relationship/network tools (get_company_connections, get_entity_graph, get_hidden_connections). There is no when-not guidance and no prerequisites stated, leaving the agent to infer selection.

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