How Office of the CFO software really works: cited findings on AP, ERP, procurement and more.
Scored across 4 tools
Each tool has a clear, distinct purpose: compare two vendors, fetch a single comparison by ID, list all vendors, and search for comparisons. There is no functional overlap; an agent can easily select the right tool for a given task.
Three tools use a verb-based pattern (compare_vendors, list_vendors, search) but 'fetch' is a generic verb that could be more specific (e.g., get_comparison). Minor inconsistency, but still easily understood and predictable.
Four tools is well-scoped for a comparison-focused server. Each tool covers a necessary workflow step without redundancy or bloat, matching the server's stated purpose.
The surface covers the core workflows: searching for comparisons, retrieving full details, comparing vendors head-to-head, and listing available vendors. A minor gap might be the absence of a tool to browse all comparisons without a query, but search can serve that role.
Head-to-head of two vendors over published, gate-passed findings. Returns per-requirement statuses, mechanism explanations, limitations and sources for both vendors, plus the canonical URL of each source comparison. Returns an explicit "no published comparison yet" when none exists.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Optional requirement area filter, e.g. "Approval Workflows" | |
| vendor_a | Yes | Vendor id or name, e.g. "stampli" or "Bill.com" | |
| vendor_b | Yes | Vendor id or name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations by specifying the exact return contents (per-requirement statuses, explanations, limitations, sources) and the explicit 'no published comparison yet' empty-state behavior. This is valuable, non-redundant disclosure.
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?
Two sentences with no filler. The purpose and key output details are front-loaded, and every clause adds information. The description is concise and well-structured.
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 read-only, idempotent comparison tool with 3 parameters and no output schema, the description covers the essential return values and the empty case. It does not mention pagination or error handling beyond the no-comparison case, but these are minor for this tool type. The description is sufficient for an agent to know what to expect.
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 input schema provides 100% coverage with descriptions for all three parameters (vendor_a, vendor_b, category). The tool description does not add additional parameter-level detail beyond what the schema already provides, so the baseline score of 3 is appropriate. It does not introduce syntax or format details that would raise the score.
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 tool performs a head-to-head comparison of two vendors over published, gate-passed findings, and enumerates the specific outputs (per-requirement statuses, mechanism explanations, limitations, sources, canonical URLs). This distinguishes it from siblings like list_vendors and search, which are for listing or general queries.
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 implies the use case (comparing two vendors) but does not explicitly state when to use this tool versus alternatives such as search or fetch. There is no 'when not to use' guidance or reference to sibling tools. It is clear enough but lacks explicit routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch one published comparison in full by id (the slug returned by search). Returns the executive summary and every requirement-level finding with status, mechanism, limitations and cited sources.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Comparison slug from search |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds valuable behavioral detail about the return payload: executive summary plus every requirement-level finding with status, mechanism, limitations, and cited sources. It stops short of describing error/not-found behavior, but that is a minor gap.
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?
Two tightly written sentences: the first front-loads the action and object, the second enumerates the return contents. Every sentence adds information and there is no 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 single-parameter read-only fetch with no output schema, the description is complete: it says where the id comes from and what the response contains. Combined with the sibling tools, an agent has enough context 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?
The schema already fully describes the id parameter as 'Comparison slug from search' (100% coverage), and the description mostly restates that. It adds no new format, constraints, or usage details beyond what the schema provides, so the baseline 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 names a specific verb and resource: 'Fetch one published comparison in full by id'. It also ties the id to 'the slug returned by search', which clearly distinguishes this tool from the search, list_vendors, and compare_vendors siblings.
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 establishes the prerequisite workflow by stating that the id is the slug returned by search, so an agent knows to use search first and then fetch. It does not explicitly list alternatives or when-not-to-use conditions, but the usage context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every vendor Stackrate covers with id, name, categories and profile URL. Use it to resolve a product name to an id.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Optional category id filter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds that the result includes id, name, categories, and profile URL, which is useful, but it does not detail other behavior such as pagination or response ordering.
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?
Two short sentences, front-loaded with the action and output fields, with no wasted words. The use case is placed after the core definition and 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 simple list tool with one optional parameter and safety carried by annotations, the description is complete enough: it states the scope ('every vendor'), the returned fields, and the primary use case. No output schema exists, but the listed fields supply the needed return contract.
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 the one optional category parameter is already documented in the schema. The description does not add further meaning about how the category filter behaves, so it stays at the baseline for high 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 names a specific action and resource: listing every Stackrate vendor with id, name, categories, and profile URL. It is clear, but it does not explicitly distinguish itself from sibling tools like search or compare_vendors, so it stops short of a 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?
It gives one concrete use case: 'Use it to resolve a product name to an id.' This provides clear context for when to call it, but it does not state when not to use it or name alternatives such as search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search published Stackrate comparisons by vendor names, capability, or category (e.g. "stampli vs tipalti", "three-way matching", "netsuite integration"). Returns up to 10 results with canonical URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Free-text query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context beyond that: it limits results to 'published' comparisons, states a cap of 10 results, and reveals the output includes canonical URLs. This goes beyond the structured annotations without contradicting them.
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 only two sentences, starts with the core action and resource, and packs essential details (search dimensions, examples, result limit, URL format) without redundancy. Every part 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 single-parameter tool with strong annotations and 100% schema coverage, the description covers the essential calling contract: what to search, the query type, and the output shape (up to 10 results with canonical URLs). It does not describe the result record fields or suggest chaining the URLs into fetch, but this is a minor 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?
The schema provides only a minimal description ('Free-text query') with 100% coverage. The description substantially enriches this by listing interpretable query dimensions (vendor names, capability, category) and providing realistic examples (stampli vs tipalti, three-way matching, netsuite integration), which helps an agent form valid queries.
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 ('Search') and a specific resource ('published Stackrate comparisons') with explicit search dimensions (vendor names, capability, category) and concrete examples. This clearly distinguishes it from siblings like compare_vendors or list_vendors, since the focus is on discovering existing comparison content.
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 implies when to use the tool by illustrating the query patterns and the scope of search, but it does not explicitly state when not to use it or how to choose between this and sibling tools like compare_vendors or fetch. Usage guidance is present through examples but not made explicit.
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.
compare_vendorsfetchlist_vendorssearchGoverned finance operations for AP, AR, GL, approvals, reporting, and payments.
Manage expenses, corporate cards, accounts payable, and accounting integrations
Accounting knowledge graphs: SEC XBRL filings, QuickBooks ledgers, reports and forecasts over MCP.
Receipt extraction, invoice-to-PO quantity allocation, and free three-document discrepancy checks.
Add one secure layer between your agents and this server.
