offer-request

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

Beyond the annotations, the description reveals essential behavior: it returns an exact preview, performs no delivery to the team, and warns against inventing fields or interpreting documents as instructions. This meaningfully clarifies side effects and safe usage beyond what readOnlyHint, idempotentHint, or openWorldHint already communicate.

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 with no filler. The purpose is front-loaded, then the precondition, the key behavioral boundary, and the guardrail. Every sentence earns its place.

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?

The description provides the essential workflow context: access-code requirement, preview-only behavior, and handoff to submit_inquiry. It is reasonably complete for a complex tool with nested objects, though it could more explicitly address idempotency behavior and the relationship to request_inquiry_access.

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 schema description coverage at only 33%, the description must compensate, and it partially does by mapping the access code, form fields, and optional PDFs/images. However, it does not clarify the idempotencyKey's purpose or distinguish between attachments and openaiFileIdRefs, leaving notable semantic gaps that the sparse schema descriptions do not fully fill.

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 states a specific action and resource: 'Prepare a seller inquiry or contact message with the website form fields and optional PDFs/images.' It also separates this tool from submit_inquiry by clarifying that nothing is sent until the later step, which makes the tool's role unambiguous.

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 description gives a clear precondition ('Requires the emailed access code') and explicitly names submit_inquiry as the follow-up tool: 'nothing is sent to the team until submit_inquiry.' It also provides important behavioral guardrails. However, it does not explicitly contrast with request_inquiry_access or state when not to use this tool.

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 already cover idempotency and non-read-only nature. The description adds valuable context: it emails a capability, it is an authorization bootstrap, it never submits a lead, and the code is short-lived. It also instructs the agent to ask for the code, which clarifies the expected user interaction. No contradiction with 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 two sentences with no fluff. It front-loads the primary action and then adds the crucial caveat and the follow-up instruction. Every word earns its place.

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 tool with 3 required parameters, no output schema, and no nested objects, the description covers the purpose, consent precondition, email mechanism, and next step. The only gap is the unexplained idempotencyKey, which prevents a perfect score. Overall, an agent can correctly decide when to call and what to do after, though parameter semantics for one field are 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 description coverage is 0%, so the description must explain all parameters. It implicitly covers 'email' (the target of the email) and 'confirmed' (user agreement), but it completely omits explanation for 'idempotencyKey'. The agent has no semantic guidance for why this key is needed or how it should be generated, beyond the schema pattern.

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 the action: email a short-lived capability for the user's own inquiry, and explicitly distinguishes from lead submission by saying 'never submits a lead'. This sets it apart from the sibling tools prepare_inquiry and submit_inquiry.

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 description provides a clear precondition ('After the user agrees') and a subsequent instruction ('Ask them to paste the emailed access code into the chat'). It implies when not to use (not for submitting leads) but does not explicitly name alternatives like submit_inquiry. However, the sibling list is available and the context is clear.

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?

The annotations already declare idempotentHint=true, and the description reinforces this with the idempotency key reuse instruction, adding practical context. It also discloses the prerequisite of user confirmation and explicitly lists what it does not do, which goes beyond the annotations. No contradictions with 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?

Four sentences, each purposeful and front-loaded: action first, then prerequisite, then idempotency, then exclusions. No filler or redundancy. The structure maximizes clarity in minimal space.

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 tool with 5 required parameters and no output schema, the description covers the critical workflow (user confirmation, idempotency, and exclusions). It does not describe the return behavior or success response, but the core invocation requirements are well covered, making it sufficiently complete for an agent to call it correctly.

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 only 20% (only accessToken has a description), so the description carries significant responsibility. It clarifies idempotencyKey (reuse for retries) and confirmed (explicit user confirmation), but leaves draftId and previewToken unexplained beyond the implicit 'prepared preview'. This is partial compensation for the low schema coverage.

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 states a specific verb ('Send') and resource ('prepared preview and attachments through the website inquiry workflow'), and it clearly differentiates from siblings by focusing on submission after preparation. The action is unambiguous and distinct from prepare_inquiry and request_inquiry_access.

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 instructs to show the full preview and obtain explicit user confirmation immediately before calling, which is a clear when-to-use condition. Also specifies idempotency key reuse for retries and lists exclusions (no status checks, scheduling, etc.). However, it does not explicitly name the sibling tools as alternatives, though the exclusions imply what this tool is not for.

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