Dominick Prevete: Instant Term Sheet

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

The description adds substantial behavioral detail beyond the annotations: it clarifies that nothing is priced, stored, or sent, and explains the reviewer-mode treatment for test email domains. These specifics confirm and enrich the read-only, idempotent, non-destructive profile declared in the annotations.

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 its core purpose and packs a lot of useful detail into a single paragraph. Some sentences are long and semicolon-heavy, but each sentence carries relevant information for an agent deciding whether to use this preparatory 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?

Given the absence of an output schema and input parameters, the description does a thorough job covering scope, required request details, read-only behavior, and reviewer mode. It claims to provide every field and accepted value but does not enumerate them here, which is acceptable for a description but leaves minor room to be more self-contained.

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 describe required request fields (full street address components) for the target request, but these are not parameters of this tool itself, so the baseline remains appropriate.

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 that the tool provides the requirements for an Instant Term Sheet request, including fields, scope, and expected return. It implicitly differentiates from the sibling request_instant_term_sheet by framing itself as the pre-request information source, though it does not name the sibling explicitly.

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 gives a clear when-to-use signal: 'before you make one,' directing the agent to consult this tool before submitting a request. It does not explicitly name or exclude the sibling submission tool, but the context makes the relationship obvious.

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?

Annotations establish the write-ish, non-idempotent, open-world profile, and the description adds genuinely useful context on top: the term sheet is emailed with a private download link, it is indicative and not a commitment to lend, and requests outside the program fit get a 24-hour manual answer. It does not cover rate limits or what an insufficient request returns, so it is not exhaustive.

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 what the tool does and the delivery/timing caveats, then closes with the prerequisite. Four sentences with no filler, though the address sentence partially duplicates schema content and could be trimmed.

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 six-parameter, six-required-object request tool with no output schema, the description covers delivery channel, timing expectations, the non-binding nature of the output, and the prerequisite tool. What an agent gets back in the instant vs 24-hour case is only loosely implied, leaving a small gap.

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 description coverage is 100%, so the baseline is 3, but the description adds emphasis on the one field most likely to be botched: a full street address with number, street, city, state and ZIP on every request, purchase or refinance, with partial/placeholder input refused. That is a meaningful addition beyond the schema's own wording.

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 (request) and resource (written term sheet) with the qualifying scope: business-purpose loan on a non-owner-occupied 1-4 unit investment property. It also names the sibling instant_term_sheet_requirements, so an agent can distinguish the two without opening either 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?

Gives clear operating conditions (instant when the deal fits the programs, otherwise an answer within 24 hours) and an explicit prerequisite: read instant_term_sheet_requirements first. It does not spell out exclusions such as owner-occupied or >4-unit deals beyond the scope phrase, so it falls short of the 5-level when/when-not/alternatives treatment.

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