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

Adds real context beyond the annotations: nothing is reached or emailed, the contact is easily reversible ('archive ... with one click'), so no confirmation is required ('does not wait for your OK'), plus the auth requirement (Cotlet API key with app access). This directly enriches the safety profile that readOnlyHint=false/destructiveHint=false only partially convey.

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-loads the purpose and keeps every sentence informative. The middle sentence ('It reaches nobody and sends no email, and you can archive...') is slightly convoluted and could be tightened, but no filler is present.

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?

Covers the key things an agent needs for a create tool: what is created, that it returns an ID, that no notifications fire, that it is reversible without confirmation, the duplicate risk, and the auth requirement. No output schema exists, but the description notes the returned ID, which is sufficient.

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%, so all four parameters are already documented in the schema. The phrase 'a person or a company' loosely gestures at is_company but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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 and resource ('Add a customer contact, a person or a company. Creates one contact and returns its ID'), so the agent knows exactly what is produced. It references list_contacts, giving partial sibling differentiation, though the distinction is framed around duplicate-checking rather than the create-vs-list choice itself.

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?

Explicitly routes the agent to a prior step ('Check list_contacts first') and explains the consequence of skipping it ('this call does not stop you from creating a duplicate'). Clear context and a named alternative, but no explicit when-not-to-use beyond the duplication caveat.

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