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

With no annotations provided, the description carries the full burden. It clearly implies a read-only operation ('List') and explains that addresses are separate records, which is important behavior not evident from the name alone. However, it does not mention potential errors when both or neither ID is passed, or whether empty results are possible, but for a simple list tool this is adequate.

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 only two sentences, with the core purpose and usage rule front-loaded. The second sentence adds a valuable clarification without redundancy. Every sentence serves a purpose, and there is no fluff.

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 simplicity (no output schema, only two optional parameters), the description is essentially complete. The main information an agent needs—what it does, when to use it, and parameter constraint—is covered. A minor omission is not specifying what happens if both or neither IDs are passed, but this could be inferred from the instruction 'exactly one' and may not be necessary.

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?

The schema provides descriptions for both parameters (companyId and contactId) with 100% coverage, so the schema already explains them. The description adds the crucial semantic that exactly one must be provided, which is not in the schema. This goes beyond the schema and clarifies the mutual exclusivity, providing added value.

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 'List the addresses on a contact or company' with a specific verb and resource. It also distinguishes itself from related tools like contacts_get and companies_get by noting that addresses are separate records, which differentiates it from siblings that might also fetch contact or company data.

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 explicitly instructs to 'Pass exactly one of contactId / companyId', providing a clear usage rule. It also guides when to use this tool ('when asked where somebody is') and when not to (addresses do not appear in contacts_get or companies_get), effectively distinguishing it from those alternatives.

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