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

The destructiveHint=true annotation covers the write/irreversibility profile, and the description adds genuinely non-obvious behavior: company names must be unique, an omitted assigned_to triggers an extra GetUser call, and a missing company is created implicitly. The implicit company creation is a real side effect an agent needs to know. It does not describe failure behavior on duplicate company names.

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?

Four tight sentences, front-loaded with the person/company distinction, then the behavioral caveats. The trailing 'LACRM: CreateContact.' is a redundant endpoint label that restates the name rather than earning its place, which keeps this from a 5.

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?

There is no output schema, but the description supplies the return shape ('Returns { ContactId }'), and all 12 parameters are documented in the schema including nested objects. Combined with the noted side effects, an agent has enough to call this correctly; only error/duplicate-handling is unaddressed.

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 the baseline is 3, but the description adds meaning the schema does not: the person/company branch of company_name, its create-if-missing behavior, and the default-plus-hidden-cost of assigned_to. Those are real semantic additions, though most of the remaining 10 parameters are left to the schema.

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 ('create a new contact (person) or company record') and immediately distinguishes the two record types, which is the key fork in this tool. An agent can tell it apart from lacrm_edit_contact or lacrm_search_contacts without opening the schema.

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?

It explains the semantics of specific parameters (when company_name applies, what happens if assigned_to is omitted), which implies usage, but never says when to pick this tool over siblings like lacrm_edit_contact or lacrm_search_contacts, and gives no exclusions. Usage is inferable but not spelled out.

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