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

Adds substantial context beyond the annotations: wrong field names are silently ignored, accounting records trigger a QuickBooks/Xero sync side effect, and the call returns the new RecordID. The 'Not idempotent' sentence merely restates idempotentHint=false, and the destructive/openWorld traits are left to the annotations, but the silent-failure and external-sync disclosures are the kind of thing annotations cannot convey.

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 operation class and verb, then layered constraints in descending importance; nearly every clause is actionable. The example lists (Estimate, Invoice, Item, Vendor) are somewhat expendable given the schema's own examples, keeping it just short of 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?

For a 2-parameter but nested/any-table mutation with no output schema, it covers everything an agent needs: eligibility check, field-name resolution, dropdown encoding, unsupported child lines, external sync consequences, and the returned RecordID. Nothing material is left to inference.

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% and the schema already documents the exact-name matching, case sensitivity, silent-ignore behavior, and the `_RecordID` integer convention for dropdowns. The description restates the same guidance rather than adding new syntax or format detail, so the baseline 3 applies.

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?

Starts with an explicit category marker and verb+resource ('WRITE: creates a record in any table that allows it'), then narrows scope immediately: customers/leads and activities go to dedicated tools, child lines are unsupported here. An agent can distinguish this from method_create_customer, method_create_activity, and method_update_record without opening any 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 when-to-use (any table where method_list_tables shows canCreate), when-not (Customer/lead and Activity records, InvoiceLine child lines), and the prerequisite ordering (call method_get_table_fields before creating). It even names the alternative tools rather than leaving the agent to guess.

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