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

Annotations are weak (all hints false), so the description carries the burden and delivers the key trait: no email/send side effects, with sending delegated to the agent and ladder advancement delegated to letter_sent. It also implies preview/re-issue behavior via the stage override. It does not cover error handling or authentication, but the core side-effect disclosure is present and does not contradict the annotations.

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?

Three sentences with the action front-loaded, each earning its place: purpose/stages/formats, the no-send behavioral disclaimer, and the letter_sent handoff. No filler and no repetition of what the schema already documents.

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 4-parameter render tool with no output schema, the description plus a fully described 100%-coverage schema gives the agent everything needed to call it correctly: invoice id format, stage semantics, date default with late-fee/deadline behavior, and format options. The return value is only loosely specified as 'the letter text,' and error behavior for edge cases (e.g., already-paid invoices) is unstated — minor gaps.

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 baseline is 3, but the description adds real meaning beyond the schema by mapping the stage enum to polite reminder, firm reminder with late-fee note, and final notice. It also reinforces the format enum as Markdown or self-contained printable HTML.

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 ('generate'), resource (the chase letter for an unpaid invoice), and the scope of the ladder's three stages ('reminder 1... reminder 2... final notice'). It explicitly distinguishes itself from the sibling letter_sent by assigning that tool the recording role, so an agent can tell them apart without opening 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?

Defines the full workflow: render here, send yourself, then record with letter_sent so the ladder advances. It names the sibling tool and the condition under which it follows, and it explicitly warns that nothing is emailed or sent by this tool — an important when-not expectation that prevents the agent from assuming the act of sending is handled.

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