underwriter-execute

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

Annotations already declare destructiveHint: true and readOnlyHint: false; the description confirms and contextualizes this by warning about 'bearer-auth requirements for protected routes' and mentioning decimal-amount-as-string encoding in the schedule preview payload. That specific encoding detail is exactly the kind of non-obvious behavioral disclosure that the agent needs to invoke correctly on live API routes.

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, zero filler, maximal information density. Every clause either names the tool's purpose, references the prerequisite discovery workflow, or surfaces a non-obvious API quirk. The awaited 'schedule preview' detail is placed strategically after establishing the alternative-tool-first mandate, so the structure guides the agent's reading order.

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 execute tool with 8 parameters, no enum values, and no output schema, the description carries a huge burden—and it delivers. It covers the authentication prerequisites, points to the discovery sibling for request contracts, names the encoding gotcha, and links the mutation flags (confirmMutation) to 'live API actions' implicitly. The 'decimal amounts encoded as strings' note seems to address a known failure mode. This is a complete briefing packet, not just a description.

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 earns an extra point by revealing cross-parameter behavior: the relationship between action values like 'previewSchedule' and the schedule preview payload's string-encoded decimals, plus the fact that headers are 'allowlisted' and that UNDERWRITER_AUTH_TOKEN is authoritative. It adds meaning to parameters that the schema alone doesn't convey.

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?

Uses a specific verb+resource construction ('Execute Underwriter API actions') and immediately orients the agent to the companion workflow by naming underwriter-discover explicitly. It clearly positions itself as the executor of actions that require prior discovery of contracts, which differentiates it from siblings. The description adds genuine semantic weight beyond the tool name alone.

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?

Explicit command: 'Use underwriter-discover first to inspect bearer-auth requirements for protected routes, loan product path/query contracts, and the schedule preview payload.' This tells the agent exactly when to use the sibling tool versus this one, and what specific things to check (auth requirements, path/query contracts, schedule preview payload). This is textbook 'when-to-use vs. alternative' guidance.

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