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

Annotations only declare readOnly=false, destructive=false, openWorld=true. The description goes well beyond: it explains the partial/unapplied-balance consequences of amount, that send_email triggers an outbound client confirmation, that a confirmation step is applied by default, and that a Cotlet API key with app access is required.

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 core action and amount behavior, then defaults and safety notes. Mostly every sentence earns its place, though 'Records a payment for the invoice client and applies it to the invoice' partially restates the opening line.

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 mutation tool with external side effects (client email, invoice status changes, confirmation gating, auth requirement) and no output schema, the description covers everything an agent needs to invoke it safely and correctly.

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 already 100% and documents most defaults, but the description adds real semantics the schema lacks: the downstream invoice-status effect of an amount below vs. above the balance, and why the payment_date matters for reports.

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 specific verb+resource ('Record money received against an invoice') and immediately names the key fields involved (date, type, bank reference). It is clearly distinguishable from siblings like list_payments or send_invoice 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 concrete usage context: the amount rules (default full balance, partial, overpayment), the payment_date guidance tied to reporting, and the send_email default. It never names a sibling alternative explicitly, so it stops short of a 5.

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