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

Annotations declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, and the description enriches this substantially: it sends real email to external recipients ('reaches other people'), requires confirmation before each call by default (toggleable per tool), and needs a Cotlet API key with app access. This adds auth, side-effect, and confirmation context well beyond the structured hints.

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-loads the core purpose and is generally well organized. Slight redundancy in the confirmation guidance ('By default you confirm each call; you can switch that off' followed by 'confirm with the user before each call'), and the 'Sends statements the way Sales > Customer statements does' sentence is somewhat 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 7-param mutation/email tool with no output schema, the description covers purpose, per-type semantics, zero-balance handling, message constraints, confirmation policy, and auth requirements. An agent has everything needed to invoke it correctly and safely.

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 schema already documents all 7 params, but the description adds real meaning: it clarifies the invoice-vs-activity semantics of statement_type, the include_zero default behavior, and that message is free text with no email variables. It exceeds the baseline 3 by explaining intent, not just repeating field names.

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 ('Email a customer statement as a PDF') and enumerates the two statement types with their distinct semantics (invoice = unpaid invoices at statement date; activity = invoices and payments between two dates). An agent can distinguish this from myob_send_invoice, which emails a single invoice rather than a statement.

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 clear context: it behaves like Sales > Customer statements, and explains when each statement_type applies and the zero-balance exclusion rule. It stops short of explicitly naming or excluding the sibling send_invoice tool, leaving the statement-vs-invoice choice to inference.

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