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

With readOnlyHint=true already declared, the description adds substantial context the annotations cannot: the token's 30-minute expiry, its exact scoping (this template, letter type, print options, recipient set, return address), what gets computed (address check, cost estimate, blank-page surcharge), and that no mail is sent here. Nothing contradicts the readOnly/idempotent hints.

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 tight paragraphs: the mandatory-step requirement and token semantics lead, the approval workflow follows. Every sentence carries actionable information with no repetition of schema fields.

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 preview tool with no output schema, the description still tells the agent what comes back (rendered letter on real data, address availability, cost estimate, confirmation_token) and the full lifecycle constraint on the token. Nothing needed to invoke or follow up 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 the baseline is 3; the description goes beyond it by explaining that print options and the return address are part of the binding token scope, and by noting the Insert Blank Page address page affects the cost estimate. It stops short of mapping each individual parameter, which the schema already handles well.

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 names a specific verb (renders/checks/estimates/returns token) and resource (letter campaign preview), and clearly separates it from the sibling preview tool (spur_preview_letter_template) and the downstream action (spur_send_letters). An agent can identify this as the mandatory pre-send rendering step 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?

It states an explicit precondition ('Required step before mailing letters') and an explicit sequence: show the preview, get user approval, then call spur_send_letters with the token, noting the widget Send button is equivalent. Both when-to-use and the alternative path are spelled out.

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