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

Annotations cover the safety profile (readOnly, non-destructive, openWorld), and the description adds rich context on top: billing is triggered only when an address is found, first call may be slow with a documented retry pattern, and it previews the return shape (verified address, confidence score, reach note). That is exactly the behavioral disclosure annotations cannot supply.

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?

Front-loaded with purpose, then inputs/outputs, cost, and retry behavior — each sentence earns its place. The closing pairing sentence is longer and more narrative than the rest, but it does route an agent toward a real workflow.

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 no output schema, the description still explains what comes back (address, confidence score, reach note), the cost model, the latency/retry quirk, and the inputs. An agent has everything needed to invoke it correctly and interpret the result.

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 only 25% (only 'role' documented), so the description carries most of the burden and does describe the three required inputs semantically. It also adds nuance for 'role' (founder/CEO first-name matches rated high confidence), though it omits format details like whether the domain should include scheme/www.

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+resource with scope: 'Find a real, deliverable professional email for a person at a company' and specifies the required inputs (first name, last name, company domain). It implicitly separates discovery from adjacent siblings like validate_email and enrich_email, but never names them, so the differentiation is left to inference.

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?

Gives concrete usage context: pass first + last name + domain, charges 1 credit only on success, retry with identical args if no matches come back, and a pairing workflow with scan_agent_readiness. Strong guidance, but no explicit when-NOT-to-use or an alternative for the same task (e.g. validate_email for an address already in hand).

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