Search 20,000+ corporate KPIs and 30,000+ source-attributed industry benchmarks. For any metric, get a plain-language definition, the formula, and how it is computed, then pull benchmark values with citations to compare performance across industries. Built for finance, operations, and analytics teams, and the agents that assemble their dashboards, scorecards, and OKRs. Free to search; benchmark values require a free account.
Scored across 3 tools
Each tool targets a distinct action and resource: search_kpis for discovery, get_kpi for full KPI intelligence, and get_benchmarks for benchmark source data. The descriptions explicitly clarify the boundary (benchmark values come from get_benchmarks, kpi_id comes from search_kpis), leaving no realistic chance of misselection.
All three names follow a clean verb_noun snake_case pattern (search_kpis, get_kpi, get_benchmarks). The verb choice (search vs get) reflects the actual distinction between discovery and retrieval.
Three tools is on the lean side, but for a read-only KPI lookup service each one earns its place: discovery, detailed intelligence, and benchmark retrieval are genuinely distinct operations. It is slightly thin but well-scoped for the purpose.
The core lookup lifecycle (search -> get details -> get benchmarks) is fully covered, and get_kpi even surfaces related KPIs and groups. Minor gaps exist, such as no direct KPI-group browsing or pagination beyond 10 search results, but agents can work around these via keyword queries.
Benchmark data for a single KPI (one kpi_id per call): benchmark values with descriptive metadata (industry, geography, time period, sample size) and full source attribution (source name, URL, excerpt, and comments). Each response includes a citation URL.
| Name | Required | Description | Default |
|---|---|---|---|
| kpi_id | Yes | The KPI slug from search_kpis. Single value only — no arrays or wildcards. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish this is a non-destructive, non-open-world read, and the description usefully adds what the read actually returns — benchmark values, industry/geography/period/sample-size metadata, source name/URL/excerpt/comments, and a citation URL. That return-content detail is meaningful since there is no output schema, though limits such as availability or missing-data behavior are not covered.
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 dense sentence with the scope constraint ('one kpi_id per call') front-loaded and no filler. It is well packed, though the trailing 'Each response includes a citation URL' partially repeats the source URL already listed.
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 carries the burden of describing the return payload and does so credibly, covering both data and provenance. For a one-parameter read tool with full annotation coverage, an agent has enough to invoke it correctly, though guidance on what to do when no benchmark exists is absent.
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 schema already declares 'Single value only — no arrays or wildcards', which the description's 'one kpi_id per call' merely restates. The description adds no new parameter semantics beyond the schema.
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+resource: retrieves benchmark data for a single KPI, and enumerates what comes back (benchmark values, descriptive metadata, source attribution). It does not explicitly contrast itself with get_kpi or search_kpis, so the sibling differentiation is only implied by the 'one kpi_id per call' scope.
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 'one kpi_id per call' phrasing implies this is a single-item lookup rather than a search, which is useful, but the description never states when to use this instead of get_kpi or search_kpis. That routing information exists only in the schema's reference to search_kpis, not in the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full intelligence for a single KPI: definition, standard formula, common pitfalls, improvement levers, related KPIs, the KPI groups it belongs to, and metadata about its available benchmarks (benchmark values themselves come from get_benchmarks). Takes the kpi_id (slug) returned by search_kpis.
| Name | Required | Description | Default |
|---|---|---|---|
| kpi_id | Yes | The KPI slug from search_kpis, e.g. "asset-maintenance-ratio". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly=true, openWorld=false, and destructive=false, lowering the bar. The description adds meaningful context by enumerating the returned content and clarifying that benchmark values are excluded (retrievable via get_benchmarks), which shapes the agent's expectation of what this call actually yields.
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 dense sentence, but every clause earns its place by naming a distinct piece of returned content or a routing hint. Front-loaded with the tool's purpose, though the long enumeration makes it slightly heavy.
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 compensates by listing the fields returned and explicitly deferring benchmark values to a sibling tool. For a one-parameter read tool with annotations covering safety, nothing an agent needs to invoke it correctly appears 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 100% and the single parameter is fully documented as the KPI slug with an example. The description restates the same slug-from-search_kpis guidance without adding format or edge-case detail beyond the schema — baseline 3.
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?
Names a specific verb and resource (retrieve full intelligence for a single KPI) and enumerates exactly what the response contains: definition, formula, pitfalls, levers, related KPIs, groups, and benchmark metadata. It also distinguishes itself from siblings by pointing to get_benchmarks for actual values and search_kpis for the id.
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?
Clearly states the prerequisite: the kpi_id slug must come from search_kpis, and it routes value lookups to get_benchmarks. This gives an agent a clear context for when this tool is the right call, though it stops short of an explicit when-not-to-use rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search KPI Depot's library of 20,000+ corporate KPIs by keyword, with optional corporate-function and industry filters. Returns up to 10 relevance-ranked matches, each with a one-line definition, its benchmark count, and the KPI's page URL. When no KPI matches the full query, the response also includes close_matches (nearest KPIs, with which query words each missed) and related_groups (KPI groups whose names match the query, with their top KPIs). Use this first to find the kpi_id (slug) required by get_kpi and get_benchmarks.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Free-text search term, e.g. "maintenance", "customer churn", "days sales outstanding". | |
| function | No | Optional corporate function filter. | |
| industry | No | Optional industry sector filter. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false, destructiveHint=false, so the safety profile is covered; the description goes well beyond that by disclosing the result cap (up to 10), relevance ranking, per-match payload, and the two fallback structures (close_matches and related_groups) returned when nothing matches. That fallback behavior is non-obvious and materially affects how an agent should react to a miss.
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, front-loaded with the core action and followed by return shape, fallback behavior, and routing order. Every sentence earns its place, though the close_matches/related_groups sentence is dense and could be split for easier parsing.
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 shoulders the return-value burden and does so: it names the fields returned per match, the match cap, and the degraded-response structures. Combined with the sibling routing, an agent has everything needed to call it and interpret results.
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 100% and both enum parameters are fully enumerated, so the schema carries most of the load. The description adds that query is free-text and that function/industry are optional filters rather than required scoping, which slightly sharpens usage beyond the schema 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 (search), resource (KPI Depot's library of 20,000+ corporate KPIs), and scope (keyword plus optional corporate-function and industry filters). It immediately distinguishes itself from get_kpi and get_benchmarks by describing a discovery/search role rather than a lookup role.
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 'Use this first to find the kpi_id (slug) required by get_kpi and get_benchmarks', naming both siblings and the ordering constraint. It also clarifies that function and industry are optional filters, so the agent knows a bare query is valid.
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.
get_benchmarksget_kpisearch_kpisDeep fundamental data & SEC filings from public companies — operating KPIs not even in Bloomberg.
Read-only public-company financials, KPIs, benchmarks, filings, and insider activity.
116 marketing, RevOps and SaaS calculators with benchmarks, guided reviews, content search, booking.
Free creator rate benchmarks and brand-offer checks, with sources. No login, no API key.
Add one secure layer between your agents and this server.
