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

Annotations only flag openWorld/write behavior; the description goes well beyond them by disclosing that the send is immediate ('the customer receives it at once'), uses your own sender address and email template, that drafts are rejected, that per-call confirmation is the default and can be toggled, and that it requires a Cotlet API key with app access. This is exactly the extra context the agent needs for an irreversible external action.

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 action in the first sentence, but the confirmation guidance is split across two sentences ('By default you confirm each call...' and 'Reaches other people: confirm with the user before each call') that partially restate each other.

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 an email-send tool with no output schema, the description covers purpose, precondition, side effects, confirmation policy, and auth requirements. Nothing needed to invoke it correctly is missing.

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 both optional parameters ('to', 'message') are already documented with their defaults. The description largely restates that behavior (contact email vs. passed address, saved template), adding little beyond the schema, 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?

States a specific verb (Email/Send), the exact resource ('a finalised invoice or quote'), and the mechanism ('with its PDF attached'). This distinguishes it from close siblings like finalize_document and download_document_pdf without needing to open their schemas.

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 a clear precondition/negative case ('A draft cannot be sent'), which implies the finalize step must run first, plus a confirmation workflow ('confirm with the user before each call'). It stops short of explicitly naming finalize_document as the prerequisite tool, so it's strong context without full alternative routing.

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