Apideck Unified API MCP — 330 tools across 200+ SaaS connectors (accounting, CRM, HRIS, ATS).
Scored across 4 tools
Each tool occupies a clearly separate role: discovery (list_tools), schema introspection (describe_tool_input), execution (execute_tool), and scope enumeration (list_scopes). Although list_tools and describe_tool_input are related, the descriptions make the boundary explicit (names vs. input contract), so misselection is unlikely.
All four tools use snake_case with a verb-first pattern (describe_, execute_, list_, list_); describe_tool_input is slightly longer but follows the same convention. There is no mixing of camelCase or vague bare verbs.
For a meta/gateway server that proxies dynamically discovered tools, four tools is a minimal, well-scoped set with no redundant members. Each tool maps to a distinct step in the discover-schema-execute workflow, and scope listing rounds it out.
The core lifecycle of a dynamic tool gateway (discover, inspect input, execute, list scopes) is fully covered. The only minor gap is the absence of an output-schema or result-contract introspection counterpart to describe_tool_input, which agents can typically work around by executing and observing.
Return the JSON-Schema input contract for a tool by name.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Exact tool name to describe (e.g. "accounting-invoices-create"), as returned by list_tools. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, indicating this is a safe read operation. The description adds little behavioral context beyond the purpose itself; it does not mention error cases (e.g., unknown tool name) or the exact format of the returned schema. 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 a single, focused sentence stating the exact operation. No filler or repetition; every word contributes to the meaning.
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 one-parameter introspection tool with strong annotations, the description sufficiently covers its return value. However, it lacks any note about behavior when the tool name is invalid, which might be useful but is not critical given the tool's simplicity.
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% with a descriptive parameter entry for 'name' including an example and source ('as returned by list_tools'). The description itself adds no parameter-specific meaning, so it relies on the schema, which is adequate.
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 a specific verb 'Return' and a well-defined resource: 'the JSON-Schema input contract for a tool by name.' This is unambiguous and distinguishes it from siblings like execute_tool or list_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?
No guidance is provided on when to use this tool versus alternatives. Siblings are listed but not compared, and there is no mention of prerequisites or typical workflows (e.g., 'use before calling execute_tool'). The implied use case is not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Invoke a tool by name. input is validated against the target schema before dispatch.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Exact tool name to invoke (e.g. "accounting-invoices-create"), as returned by list_tools. | |
| input | No | Arguments object validated before being forwarded to the target tool. Its shape matches that tool's input schema (fetch it with describe_tool_input). Omit for tools that take no arguments. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds one genuinely useful behavioral fact not in the annotations: the input payload is schema-validated before dispatch. However, given annotations already flag destructiveHint=true and openWorldHint=true, the description does not warn that the target call may mutate/destroy remote state with no undo, nor mention error/propagation behavior.
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 with the core action front-loaded and zero filler; every clause carries 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?
For a destructive, open-world dispatcher with no output schema, an agent would benefit from knowing that it must discover the target tool via list_tools/describe_tool_input first and that side effects are irreversible. Those gaps are real but not fatal given the strong schema.
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 baseline is 3; both parameters, including the nested `input` object and the omit-for-no-args rule, are fully documented in the schema. The description only restates that `input` is validated, adding no new parameter meaning.
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 ("Invoke a tool by name") which is unambiguous. It does not explicitly contrast itself with the read-only siblings list_tools / describe_tool_input, though the naming makes the distinction inferable.
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 dispatch role but never says when to call this versus describe_tool_input or list_tools first, nor when not to call it. The workflow hint (fetch the target schema) lives only in the schema text, not the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the list of allowed MCP scopes.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds the qualifier 'allowed,' implying scopes may be restricted, but provides no additional behavioral context beyond what annotations already convey.
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, front-loaded sentence: 'Return the list of allowed MCP scopes.' Every word earns its place, with no redundancy or unnecessary detail.
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, parameterless tool, the description sufficiently communicates the return value (a list of scopes). While it lacks details on output format or edge cases, the tool's triviality means this is adequate completeness.
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 tool has 0 parameters, and the schema is empty, so there is no parameter meaning to explain. The description is not required to compensate, and the baseline for 0-param tools is 4.
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 uses the specific verb 'Return' and identifies the resource as 'list of allowed MCP scopes,' which clearly distinguishes it from sibling tools like list_tools (which lists tools) and execute_tool (which executes 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 description provides no guidance on when to use this tool versus alternatives. It does not mention any context, prerequisites, or exclusions, leaving the agent to infer usage solely from the tool's name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Discover Apideck tools. Call with no args for domain index; filter with domain/search_terms/scope. Scoped to the connection's supported resources when service_id is set.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Filter by mutation scope: "read" (no writes), "write" (creates/updates), or "destructive" (deletes/overwrites). Omit to include all scopes. | |
| domain | No | Restrict results to a single tool domain (e.g. "accounting", "hris"). Omit to get the cross-domain index. Use a key returned by a prior no-arg call. | |
| search_terms | No | Case-insensitive substring terms ANDed across a tool name/description (e.g. ["invoice","create"]). Omit to list everything in the domain. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile needs no restating. The description adds the no-arg default behavior and the connection-scoping constraint, but the per-filter semantics it describes are already spelled out in the schema property descriptions.
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, zero filler, and the default no-arg behavior is front-loaded before the filtering options. Every clause carries 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?
For a 3-param, no-output-schema discovery tool with full annotation coverage, this is nearly sufficient: the entry mode, filters, and connection scoping are all stated. The mention of service_id, which is not an input parameter, introduces mild ambiguity about whether it must be supplied or is inferred from the connection.
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 enum on scope is documented in-schema, so the schema does the heavy lifting. The description only echoes the parameter names in one clause without adding format or interaction detail (e.g., how search_terms combine with domain).
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 ("Discover Apideck tools") and immediately clarifies the two modes: no-arg domain index vs. filtered listing. It is distinguishable from siblings like describe_tool_input and execute_tool, though it never names them explicitly.
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 concrete usage branching: no args for the domain index, domain/search_terms/scope to filter, and notes result scoping when service_id is set. Clear context, but no explicit exclusions or pointers to sibling tools for the follow-up steps (describe/execute).
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.
execute_tool1 field changedInput schema / properties / input / descriptionPrevious value: -"Arguments object forwarded verbatim to the target tool. Its shape matches that tool's input schema (fetch it with describe_tool_input). Omit for tools that take no arguments."New value: +"Arguments object validated before being forwarded to the target tool. Its shape matches that tool's input schema (fetch it with describe_tool_input). Omit for tools that take no arguments."Unified.to MCP server — one API for 500+ B2B SaaS integrations across 28+ categories
Discover, plan and run tools across your connected business systems through one OAuth MCP endpoint
Unified MCP server for 70+ eCommerce platforms: products, orders, customers, and more.
Discover and call 10,000+ production APIs from one MCP server. Pay-per-call billing for AI agents.
Add one secure layer between your agents and this server.
