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

Beyond annotations, it discloses critical behavior: the tool immediately spends the approved amount, can buy postage, sends nothing on insufficient balance, and staging prevents postage while still debiting the workspace balance. It also explains retry and reconciliation behavior for interrupted or uncertain sends.

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?

The description is front-loaded with the core action and then covers preconditions, financial effects, failure modes, and retry guidance. It is dense and somewhat run-on, but the information is largely necessary for a destructive financial tool.

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 complex destructive tool with 16 parameters, an output schema, and annotations, the description covers the essential decision context: authentication requirement, quote dependency, approval semantics, spend behavior, staging behavior, and reconciliation after uncertain sends. Return-value details are appropriately left to the output schema.

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 56%, and the description adds important meaning for the four required parameters: quoteId must come from quote_letter, confirmed must reflect explicit user approval, approvedTotalCents must match server calculation, and idempotencyKey must be generated once and reused for identical retries. It does not explain every optional parameter, but it compensates for the core high-risk semantics.

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 identifies the exact action: releasing an immutable quoteId from quote_letter to send a letter using workspace balance. It clearly distinguishes this from the quoting sibling by requiring a saved quote, confirmed approval, and matching approvedTotalCents.

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 explicit preconditions: confirmed=true, approvedTotalCents must match the saved quote, and an idempotencyKey must be used after reviewing the exact saved PDF, addresses, and options. It also gives when-not guidance such as changed content requiring a new quote and no guest payment, funding, or cryptocurrency settlement.

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