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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description doesn't need to restate safety. It adds value by explaining that withdrawn profiles are excluded from the graph. It also clarifies the nature of relationships (officers and their other companies), which is behavioral context. However, it doesn't disclose depth mechanics or output limitations beyond the schema.

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 description is concise and well-structured. It front-loads the core concept (group around a company) and then adds detail about usage and exclusions. Each sentence provides distinct value with no redundancy.

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?

Given the tool's moderate complexity (graph traversal), the description is fairly complete. It explains what the graph includes and excludes, and the schema covers parameters. However, it doesn't explicitly state the output format (though no output schema exists), nor does it mention pagination or limits, which could be important for an agent. Since there's no output schema, some return format information might be needed, but the description's core intent is clear.

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 both parameters (uid and depth) are well documented. The description does not add parameter-specific details beyond the schema, but it does explain the graph concept. Baseline 3 is appropriate since the schema carries the parameter semantics.

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 clearly states the tool's purpose: to find a group of companies connected by shared people (officers). It uses a specific verb ('get') and resource ('company network'), and explains the graph concept. It distinguishes itself from siblings by clarifying it maps people to companies, which is not covered by get_company or get_director.

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 description implies when to use this tool: when you need to find a network of companies that share people but not names. It explicitly states what is excluded ('Withdrawn profiles are left out'), providing some usage context. However, it does not explicitly mention alternatives or when not to use it, but the contrast with siblings is implicit.

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