Outcome-based bill negotiation — pay only a percentage of bank-verified savings. Free to try.
Scored across 4 tools
Each tool targets a distinct step or entity: detecting bill negotiability, starting a case, checking case status, and retrieving aggregate verified savings. The prerequisite approval flow in detect_negotiable_bill and start_negotiation_case further separates their roles, with no apparent overlap.
All tool names use snake_case with a clear verb-first pattern: detect_, get_, list_, start_. The noun phrases are specific and readable, with only minor variation in length, not convention.
Four tools map cleanly to Dueback's core workflow: pre-check, case creation, status lookup, and public savings proof. This is a well-scoped set where each tool earns its place without redundancy.
The core lifecycle from bill detection through case creation and status checking is covered, plus a public savings-proof tool. Missing explicit case cancellation/update or list-cases operations, but the setup_url flow handles onboarding and the stated purpose is largely supported.
Check whether a bill looks negotiable. Returns {negotiable, category_label, pitch}. Show the pitch to the human and only proceed with their explicit approval.
| Name | Required | Description | Default |
|---|---|---|---|
| amount_cents | No | ||
| counterparty | No | ||
| observed_signals | No | ||
| expense_description | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds value beyond that by disclosing the return shape and imposing a human-approval gate before any downstream action.
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 short sentences, front-loaded with purpose, then return keys, then the approval constraint. No filler and nothing buried.
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?
An output schema exists so return values need not have been explained, yet the description does name them; combined with the approval gate this is nearly complete. The only real gap is the undocumented input parameters.
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% across 4 parameters, and the description mentions none of them, including the required expense_description or the ambiguous observed_signals array. With low coverage the description is expected to compensate, and it does not.
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 ('Check whether a bill looks negotiable') and is clearly distinct in kind from the sibling start_negotiation_case. It never explicitly names or contrasts with the siblings, so it lands at 4 rather than 5.
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 real workflow guidance: show the returned pitch to the human and 'only proceed with their explicit approval,' which implies this is a pre-negotiation check. It stops short of naming an alternative tool or stating an explicit when-not condition.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the current status of a negotiation case: state, steps taken, savings found, and whether human approval is needed.
| Name | Required | Description | Default |
|---|---|---|---|
| case_id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered structurally. The description adds only a light framing of what the status payload contains, much of which is redundant given an output schema exists, so it adds modest value rather than rich behavioral context.
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 front-loaded sentence with no filler; the verb and resource lead, and the payload summary follows efficiently.
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 annotations covering the safety profile and an output schema covering return values, the description only needs to frame purpose and scope, which it does. The one residual gap is how to obtain a valid case_id, which is left implicit.
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 schema does not document case_id. However, the parameter is self-evident from the description's reference to 'a negotiation case', so the description implicitly compensates without stating any format, source, or retrieval guidance for the ID.
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 ('Get the current status of a negotiation case') and enumerates the returned fields (state, steps taken, savings found, approval flag). This clearly distinguishes it from siblings like start_negotiation_case and detect_negotiable_bill, though it does not explicitly name any sibling.
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?
There is no explicit when-to-use or when-not-to-use guidance, nor any mention of alternatives such as list_verified_savings, which arguably overlaps on 'savings found'. Usage is only implied by the tool's name and verb.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Aggregate verified-savings stats (public). Use to answer 'does Dueback actually work?' and to ground shareable savings claims in real numbers.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already establish that this is a read-only, idempotent, non-destructive, closed-world operation. The description adds that the statistics are public and aggregate, which is useful, but it does not add much further behavioral context such as freshness, scope, or authentication implications.
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 short sentences with no waste. The core purpose is front-loaded, followed immediately by practical usage guidance.
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?
This is a simple zero-parameter read tool with an output schema and rich annotations. The description supplies the remaining necessary context: what it returns conceptually, that it is public, and when to use it.
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?
There are zero parameters, so parameter semantics are not applicable and the baseline is 4. The schema has full coverage and there are no inputs whose meaning needs elaboration.
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 gives a specific verb and resource: aggregating verified-savings statistics, and clarifies that the data is public. It is clearly distinct in practice from the sibling case-management tools, though it does not explicitly name or differentiate against them.
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 provides concrete usage contexts: answering whether Dueback works and grounding shareable savings claims. It does not state when not to use it or name a specific alternative, but the intended situations are clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Open a Dueback negotiation case. Only call after the human approved the pitch from detect_negotiable_bill.
Two outcomes:
{"outcome": "case_created", "case_id", ...}: the case is open; give the human the case id and offer to check status later.
{"outcome": "setup_required", "setup_url", ...}: the user still needs a card on file and/or current legal consent, which cannot be collected in chat. Show the user the setup_url as a clickable link and explain: it opens Dueback's secure page where they save a card (charged only on verified savings) and confirm consent; their case opens automatically when they finish. Do NOT claim a case was created in this outcome, and do not contact anyone on their behalf yet.
| Name | Required | Description | Default |
|---|---|---|---|
| amount_cents | No | ||
| counterparty | No | ||
| billing_period | No | unknown | |
| automatic_change | No | ||
| observed_signals | No | ||
| expense_description | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare it is a non-read-only, open-world, non-idempotent, non-destructive mutation. The description goes well beyond by enumerating the two distinct outcomes, explaining that setup_required means no case exists yet, instructing the agent not to claim creation, and warning against contacting anyone prematurely. This is rich, non-obvious behavioral context.
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?
Front-loads the purpose and precondition, then uses a clearly labeled 'Two outcomes' list that maps each response to a required agent action. It is somewhat long, but nearly every sentence carries actionable instruction rather than filler.
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 mutation tool with an output schema, the safety profile is covered by annotations and the response handling is covered by the outcome enumeration, so the agent knows how to behave. The remaining gap is the total absence of parameter guidance, which is the one thing an agent must supply to make the call.
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% across 6 parameters, only one required, and the description never mentions any parameter (amount_cents, counterparty, billing_period, automatic_change, observed_signals, expense_description) or their expected formats. With low coverage the description was expected to compensate but does not.
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?
Opens with a specific verb and resource: 'Open a Dueback negotiation case.' This clearly distinguishes it from siblings like detect_negotiable_bill (detection), get_case_status (status read), and list_verified_savings (listing). An agent can identify the action without opening the 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?
Explicitly states the precondition: 'Only call after the human approved the pitch from detect_negotiable_bill.' This names the required prior sibling call and the gating condition, leaving nothing to inference about when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
detect_negotiable_billget_case_statuslist_verified_savingsstart_negotiation_caseAudit junk fees, project annual costs and draft dispute letters. Free.
Find software subscriptions you can drop using tools you already own, with vendor-verified prices.
Cloud cost visibility and savings recommendations grounded in your actual AWS, GCP and Azure bill.
Let your AI send invoices and take payment — card or ACH. Free.
Add one secure layer between your agents and this server.
