SecondAppraisal Total-Loss Intake

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

The annotations already declare read-only, idempotent, non-destructive behavior, and the description adds useful temporal detail: the confirm link is only present while the intake is still confirmable and the receipt is current/preliminary. There is no contradiction with 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 a single efficient sentence with the key scoping phrase front-loaded ('Fetch the current receipt') followed by a compact parenthetical list of response contents. No filler or repeated information.

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?

With no output schema, the description compensates by naming the main return elements: status, confirm link (with a validity condition), and preliminary data. It is slightly terse about what 'preliminary' means and does not discuss error conditions, but for a simple read-only two-parameter tool this is adequate.

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 schema already documents intake_id and poll_token, including their provenance ('from a previous submission', 'returned once on that submission'). The tool description adds no additional parameter-level meaning; it stays at the baseline for full 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 opens with a specific verb and resource ('Fetch the current receipt for a submitted intake') and then enumerates exactly what the receipt contains: status, a confirm link while still confirmable, and preliminary data. This clearly separates a read/status operation from the sibling submission and estimate tools.

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 'for a submitted intake' and 'while still confirmable' gives a clear temporal context: call this after an intake has been submitted and while confirmation is still possible. It does not explicitly name alternatives or exclusions, but the context is strong enough that an agent can infer when it applies.

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 readOnlyHint, idempotentHint, openWorldHint, and non-destructiveness, so the bar is lower. The description adds valuable context beyond annotations: 'Nothing is stored about the customer' discloses privacy/non-persistence, and 'Not an appraisal' clarifies the output's informal status. No contradiction with 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?

Three concise sentences with the core purpose front-loaded. Each sentence earns its place: purpose and outputs, formal-appraisal caveat, and privacy guarantee. No filler or redundancy.

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?

Even without an output schema, the description names the expected return components, so the agent knows what it will receive. It does not specify field names, error cases, or fallback behavior when comparables are unavailable, but for a preliminary read-only estimate with safety annotations in place, this is nearly 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?

Schema description coverage is only 38%, so the description must compensate. It adds meaning for key parameters indirectly: 'near the customer' clarifies zip, 'odometer-adjusted' clarifies odometer, and 'gap vs the insurer's offer' clarifies acv_offer_cents. However, it does not clarify trim, state, or the required vehicle identifiers beyond what the schema provides, leaving some compensation gap.

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 and resource: 'a no-commitment early market read for a vehicle' and enumerates concrete outputs (10th percentile/median/90th comparable prices, odometer-adjusted mid, gap vs insurer's offer). It also distinguishes itself with 'Not an appraisal' and, given siblings like submit_total_loss_intake and upload_valuation_report, the agent can clearly tell this is the lightweight read-only estimate 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 description clearly positions this as an early, no-commitment read rather than a formal appraisal, giving the agent context for when to invoke it. It does not explicitly name alternatives or state when not to use it, although sibling names such as submit_total_loss_intake make the boundary reasonably inferable.

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 declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds useful content-level context (what facts are returned) but does not disclose additional behavioral details such as error handling or availability of results for all states. 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?

A single sentence front-loads the core purpose with a colon and then lists specific fact categories without filler or redundancy. Every item in the list 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 one-parameter read-only lookup with no output schema, the description sufficiently explains what the tool returns by enumerating the rule categories. Nothing essential is missing for an agent to invoke 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 description coverage is 100%: the single parameter's two-letter code or state-name format is fully documented in the schema. The description does not add parameter semantics beyond the schema, so the baseline of 3 applies.

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 identifies the resource as state-specific total-loss rules and enumerates the contents, distinguishing it from the sibling tools (intake status, preliminary estimate, submission, upload). It lacks an explicit verb such as 'gets' or 'looks up', so it stops just short of top score.

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 use case is implied: an agent needing state total-loss facts (threshold, method, appraisal rules, citations, hotline) should call this tool. However, it does not explicitly name alternatives or state when not to use it, leaving the decision to inference.

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 description discloses the full side-effect profile: it creates an intake, returns a confirmation link, triggers contact policy (email/text/call), and details pricing with a card HOLD only after settlement improves. It also states 'never collect card details' and instructs to read customer_message verbatim. This goes well beyond the annotations (readOnlyHint=false, idempotentHint=true) by explaining the actual transaction flow and constraints.

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 long but dense and well-structured: it leads with the core purpose and minimum requirements, then details the output, contact policy, and pricing. Every sentence carries information necessary for correct usage (e.g., the $472 discount, the card HOLD condition, and the prohibition on card collection). It is appropriately sized for the complexity, though could arguably be tightened.

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?

With no output schema, the description fully explains the return value structure (customer_confirmation_url, customer_message, preliminary, contact_policy, pricing). It also covers operational edge cases (payment flow, who pays, when holds occur, notification options via notify_customer). An agent can act correctly without needing any additional context.

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% — every parameter already has an explanatory description. The tool description adds little beyond restating the minimum required fields (already implied by the schema's required array and the customer description) and summarizing output fields. It does not provide syntax or formatting details that the schema lacks, so the baseline of 3 applies.

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 specific verb and resource: 'Submit a vehicle owner's total-loss situation to SecondAppraisal on their behalf.' It clearly distinguishes this from the sibling tools (status, estimates, rules, uploads) by focus on submission. The intent is 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 clear context on when to use this tool: to submit a total-loss situation on behalf of a customer, with explicit minimum requirements (phone/email, agent self-ID, consent attestation). However, it does not explicitly contrast with alternatives or state when NOT to use it, so it stops short of a 5.

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 indicate a mutating, non-idempotent operation. The description adds valuable behavioral context beyond those annotations: the file is parsed for specific fields (vehicle, mileage, offer, insurer, loss date), the preliminary estimate is refreshed, and processing may take up to two minutes. This gives an agent reasonable expectations about side effects and latency.

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 three tight sentences with no filler. The first sentence states purpose, the second explains the processing side effect, and the third sets latency expectations. Every sentence earns its place and the key information is front-loaded.

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 4-parameter upload with no output schema, the description covers the action, the parsed fields, the downstream refresh, and the expected latency. It does not explicitly describe an asynchronous polling flow, but the poll_token parameter and the two-minute latency note make that behavior reasonably inferable.

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%, and each of the four required parameters already has a clear, purpose-specific description. The tool description adds useful context about what is parsed from the PDF but does not add parameter-level constraints or format details beyond what the schema already provides, so the baseline of 3 is 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 states a clear verb ('Attach'), a specific resource (the insurer's Market Valuation Report as a CCC/Mitchell PDF), and the target ('a submitted intake'), along with the downstream effect ('refresh the preliminary'). This clearly distinguishes it from siblings like submit_total_loss_intake, making the tool's role obvious.

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 makes the usage context clear: the report is attached to an already-submitted intake, and the required token is described as being returned on that prior submission. It implies the correct workflow position relative to the sibling tools, though it does not explicitly name an alternative or say when not to use it.

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