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

Annotations already flag non-idempotent, destructive and open-world, but the description adds real consequences: a second call creates a duplicate record, a full customer also appears in QuickBooks/Xero, and a primary Contact record is created as a side effect. That side-effect disclosure is genuinely beyond the structured fields. The remaining gap is the response shape, which is only partially described (contact_id).

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 a 'WRITE:' marker and the core purpose, then the mode distinction, then the side effects and prerequisites. Every sentence carries information, though the heavy parenthetical nesting makes it dense to parse.

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 9-parameter nested-object write tool with no output schema, the description covers the risky parts: duplicate creation, accounting sync, auto-created Contact, and how to address extra_fields. It stops short of describing the full returned payload (e.g. the customer's own id field name), which matters with no output schema.

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 56%, and the description compensates for the most consequential parameters: is_lead's sync semantics, name's requiredness and formatting, and extra_fields' exact-name/case-sensitivity behavior plus the `_RecordID` convention for dropdown fields. email, phone, first_name, last_name and lead_status are left to the schema, which is tolerable since they are largely self-describing.

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?

Opens with a concrete verb and exact target ('creates a record in Method's Customer table') and immediately differentiates the two modes of the resource (lead vs full customer synced to QuickBooks/Xero). An agent can tell this apart from the generic sibling method_create_record without opening either 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?

Gives explicit routing: search first with method_search_customers because the call is not idempotent, and use method_get_table_fields to discover valid extra_fields names. It also gives a conditional naming rule (use "First Last" when there is no company) and tells the agent to link activities via contact_id rather than the customer id.

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