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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by disclosing non-idempotency ('Calling it twice sends two emails'), the not-found failure mode, that external recipients are reached, the per-call confirmation default and its override, and the required Cotlet API key scope. This is exactly the external-side-effect context an agent needs before sending.

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 purpose and otherwise dense and useful. Minor redundancy between 'By default you confirm each call; you can switch that off for this tool' and 'Reaches other people: confirm with the user before each call', but each sentence still carries decision-relevant content.

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, no-output-schema mutation tool, the description covers errors, idempotency, auth, and human-confirmation requirements well. The only gap is what a successful call returns (confirmation of send, message id), which an agent might want but is not essential to invoke 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 description coverage is 100%, so both parameters are already documented. The description's 'address you give, or to the client's saved email when you give none' merely restates the schema's default for emails, adding no syntax or format detail beyond structured data. Baseline 3 is appropriate.

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 ('Send a stamped invoice or credit note to the client by email') and identifies the delivery channel (Facturama's email). An agent can immediately tell this apart from facturama_create_invoice, facturama_get_invoice, and facturama_download_invoice_file 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?

The description explains behavior rather than selection: it says the doc goes to the given address or the client's saved email, and warns about human-facing confirmation. It never names an alternative (e.g. download_invoice_file for a PDF copy) or states the prerequisite that the invoice must already be stamped. Usage is implied rather than specified.

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