Dominick Prevete: Instant Term Sheet

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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds meaningful context beyond that: 'nothing is priced, stored or sent' and a detailed reviewer mode exception where .test/.invalid or example.com emails are priced and answered without being emailed or recorded. These details help the agent understand the tool's behavior and scope.

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 purpose and packs scope, required fields, and reviewer mode into a dense paragraph with little waste. It could be slightly easier to scan with bullet points or line breaks, but it remains appropriately sized for a reference-style 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 zero-parameter, no-output-schema reference tool, the description covers the required request fields, the business scope (business-purpose loan on non-owner-occupied 1–4 unit property), and what the investor receives. Annotations already cover safety and idempotency, so the definition is complete.

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 tool has zero parameters, so the baseline is 4. The description does not need to explain parameter semantics, and it correctly avoids inventing any. The listed request fields pertain to the sibling request tool rather than this tool's own parameters.

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 opens with a clear verb-resource statement: what an Instant Term Sheet request needs, including required fields and accepted values. It explicitly distinguishes this reference tool from the request action by saying 'before you make one,' and the sibling request_instant_term_sheet is implied. An agent can immediately tell this is a read-only requirements lookup, not the submission tool.

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 phrase 'before you make one' clearly signals the intended timing and relationship to the sibling request tool. However, it does not explicitly name request_instant_term_sheet or state when-not-to-use, so the agent must infer the routing. This is clear context but short of explicit alternatives.

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

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

Adds valuable context beyond annotations: describes the non-commitment nature ('indicative and not a commitment to lend'), the output delivery ('emailed to the investor with a private download link'), timing behavior, and how options are labeled in the response. It does not restate annotation hints but enriches understanding of the operation's semantics and outputs.

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?

Reasonably concise at five sentences, with key constraints front-loaded (purpose, timing, address requirement). The inclusion of option labeling is slightly tangential but still relevant. Could be tightened by merging the address sentence with the prerequisite statement.

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 6-parameter nested request tool with no output schema, the description covers the essential operational context: prerequisites, timing, non-commitment, delivery method, and option labeling. It stops short of describing what a successful response contains in detail, but that may be intentionally left to the output of instant_term_sheet_requirements.

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?

With 100% schema description coverage, the schema already thoroughly documents every parameter. The description adds little parameter-specific detail beyond reiterating the address requirement, which is already in the schema. Baseline 3 is appropriate given the schema does the heavy lifting.

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 and resource ('Request a written term sheet for a business-purpose loan on a non-owner-occupied 1–4 unit investment property'), including scope constraints. It distinguishes itself from the sibling instant_term_sheet_requirements by framing this as the actual request action versus reading requirements first.

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?

Explicitly directs the agent to 'Read instant_term_sheet_requirements first for the fields,' naming the prerequisite sibling. It also clarifies the timing expectation ('Instant where the deal fits the programs; otherwise an answer within 24 hours') and the condition for needing a full address on every request.

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