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

Goes well beyond the destructiveHint=true annotation by explaining the actual mutation model: omitted fields are left alone (safe partial update) while multi-value fields (email, phone, address, website) are fully REPLACED by the list passed. That replacement warning is critical data-loss context the annotation cannot express.

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?

Five short sentences, front-loaded with the core update semantics and the highest-risk behavior (REPLACED) before the incidental is_company note. No filler.

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 13-parameter mutation tool with no output schema and only a destructiveHint annotation, the description supplies exactly the missing behavioral risk (partial vs replacement fields) and cross-references the helper tool for custom field discovery. Nothing essential to correct invocation is absent.

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 genuinely new meaning: the pass-through vs replace distinction across parameters and the is_company=true rename rule. It also points to lacrm_list_custom_fields for custom_fields keys.

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 ('Update fields on an existing contact or company') and the scope word 'existing' cleanly separates it from the sibling create_contact. An agent can distinguish the read/update path from creation 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?

Clear context: this is for pre-existing records, and the field-level update semantics tell the agent exactly how to call it. It does not name an explicit alternative (e.g. create_contact for new records, lacrm_get_contact for reads), so it lacks the when-not routing of a 5.

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