Draft a payment follow-up email for an overdue invoice. Returns subject + body. Does not send email — the user copies it to their own inbox.
| Name | Required | Description | Default |
|---|---|---|---|
| client_name | Yes | Client or company name | |
| days_overdue | Yes | How many days past the due date (0 = due today) | |
| invoice_amount | Yes | Invoice amount in dollars |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the output (subject+body) and the critical behavior that the tool does not send the email. This is useful, though it could mention more about how the draft is generated.
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?
Two sentences, front-loaded with the core purpose and immediately followed by a clarifying behavioral note. There is no filler or redundancy.
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 simple tool with three well-documented parameters and no output schema, the description covers the purpose, output, and the critical non-sending behavior. It is complete for an agent to understand and 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?
The input schema provides 100% coverage with clear descriptions for all three parameters (client_name, invoice_amount, days_overdue). The description adds no extra parameter semantics, so the baseline of 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?
The description clearly states the tool drafts a payment follow-up email for an overdue invoice, specifies it returns subject and body, and distinguishes it from sibling tools by focusing on email drafting rather than tips or template listing.
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 implies usage when an email draft is needed, and the non-sending note clarifies that the user must handle sending. However, it doesn't explicitly reference sibling tools or provide exclusion criteria, so it's implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clear, distinct purpose: drafting an email, getting a tip, listing templates, and recommending a template. There is minimal overlap; even though draft and recommend both relate to chase emails, they are conceptually different—one creates custom content, the other points to an existing template.
All tool names follow a consistent verb_noun pattern (draft_chase_email, get_chase_tip, list_templates, recommend_template) using lowercase snake_case. This is uniform and predictable, making it easy for an agent to infer functionality from names alone.
With 4 tools, the server is well-scoped for its purpose of assisting with invoice chase emails. Each tool addresses a core need (drafting, guidance, discovery, recommendation) without unnecessary bloat or missing essentials.
The domain is focused on providing chase-email assistance, and the tools cover the full workflow: getting context-aware tips, drafting an email, browsing templates, and getting a specific recommendation. Since sending is intentionally out of scope, there are no significant gaps.