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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by disclosing that the contact 'reaches no one' (no notifications sent), that it 'runs without asking first' (no confirmation needed), that it performs no duplicate check, and that a scoped Cotlet API key is required. These are exactly the side-effect and auth facts an agent needs and cannot get from structured fields.

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 the action and keeps strong signal early (no dedup check, no notifications, changeable later). Minor redundancy: customer/supplier/lead are enumerated at the start and the full type list is repeated immediately after, which costs a line without adding meaning.

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?

For a non-destructive, open-world create tool with full schema coverage, the description covers behavior, dedup risk, mutation path, and auth prerequisites. With no output schema, the return shape (e.g. new contact id) is unstated, a minor gap an agent would otherwise have to discover at runtime.

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 name/email/tax_id are already documented in the schema. The description restates the type enum options, which the schema already lists verbatim, adding only marginal framing ('the contact type Holded uses'). Baseline 3 is appropriate when the schema does the heavy lifting.

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, supplier or lead to Holded', 'Creates one contact'), scoping it to a single created entity. It is clearly distinguishable from siblings like update_contact and list_contacts, which it names explicitly.

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 when-to guidance: 'Search with list_contacts first: this call does not check for a duplicate' tells the agent the precondition before invoking, and it points to update_contact as the alternative for modifying an existing contact. Alternatives and conditions are both named rather than left to inference.

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