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

Beyond the annotations, the description discloses important behaviors not implied by readOnlyHint or destructiveHint: it refuses duplicate emails/phones unless allow_duplicate is true, treats company as free text rather than a linked record, and explains that one contact can be referenced by multiple leads. This gives the agent a realistic model of the tool's side effects and constraints.

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 long, but it front-loads the clear definition and each additional section addresses a real workflow concern: duplicate creation, deal/lead attachment, pre-checks, and list/collaborator semantics. It is slightly redundant with schema descriptions for company, list_id, and is_collaborator, and the ALL-CAPS directives are visually noisy, yet the structure is logical and purposeful.

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 17 parameters and no output schema, the description covers the essential edge cases: duplicate handling, lead/deal association, pre-creation lookup, and workspace-specific lists. It is complete enough to invoke safely; the only minor gap is that it never explicitly states what the tool returns, but the post-creation instructions imply the agent will know when creation succeeded.

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?

With only 53% schema description coverage, the tool description compensates for the most meaningful parameters: allow_duplicate's refusal workflow, list_id's name-or-id resolution, company's non-relational nature, and is_collaborator's distinction between working relationships and sales targets. Some remaining parameters are self-explanatory or already documented in the schema, so it does not need to cover all 17 explicitly.

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 opening sentence gives a concrete verb-resource pair: 'Create a CRM contact: a named person, with their address, phone numbers and CVR/VAT number.' It also distinguishes this tool from crm_create_deal and crm_create_lead by explaining that a contact sits outside the pipeline and that deals or leads carry the contact via contact_id.

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 gives explicit workflow guidance: check crm_get_contacts before creating from a lead, and ask whether to attach the contact to a deal after creation. It names the exact alternative tools for attaching to deals and leads (crm_create_deal, crm_update_deal, crm_update_lead) and warns against creating duplicate contacts.

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