A no-auth MCP server for searching, comparing, pricing and recommending 10,000+ software tools, with sourced and dated pricing data.
recommend_tools – Get a ranked, justified shortlist for a described need, filtering by budget, team size, category or pricing model.
search_tools – Keyword/category search across the tool database with sorting by score, recency or rating.
get_tool – Pull a full profile: pricing, pros/cons, features, editorial score, review synthesis and alternatives.
compare_tools – Side-by-side comparison of 2–4 tools with computed insights (best overall, best value, most reviewed).
get_alternatives – List direct competitors of a given tool, ranked by editorial score.
get_pricing – Detailed tiers, pricing model, free-trial status and an expert pricing verdict.
list_categories – Discover all categories and their tool counts (to find valid category slugs).
report_issue – Flag a wrong price, dead tool or bad feature to the verification queue, with optional evidence URL.
Provides access to Toolradar's data on Asana, including pricing tiers, features, scores, and alternatives, enabling AI agents to answer questions and perform comparisons.
Provides access to Toolradar's data on ClickUp, including pricing plans, features, ratings, and alternatives, allowing AI agents to recommend and compare.
Provides access to Toolradar's data on Figma, including detailed pricing tiers, features, scores, and alternatives, allowing AI agents to answer pricing queries and comparisons.
Provides access to Toolradar's data on Jira, including pricing, features, G2/Capterra ratings, and alternatives, enabling AI agents to find and recommend alternatives.
Provides access to Toolradar's data on Linear, including pricing, features, pros/cons, and alternatives, enabling AI agents to provide detailed tool information.
Provides access to Toolradar's data on Notion, including pricing, features, editorial scores, and alternatives, facilitating detailed tool analysis and comparison.
Provides data on new tools discovered via Product Hunt, enabling AI agents to recommend recently launched software tools with up-to-date information.
Provides aggregated Trustpilot ratings for software tools via Toolradar's database, allowing AI agents to include user review data in recommendations.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@toolradar-mcp Find free project management tools"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Search, compare and price 10,000+ software tools from your AI assistant. Every price comes with the date it was read on the vendor's own pricing page.
Works with Claude (Desktop, Code, claude.ai) · ChatGPT · Cursor · VS Code · Windsurf · Cline · any MCP client. No API key and no signup needed.
"Recommend a CRM for a 5-person B2B startup under $50 a month"
"Compare Notion, ClickUp and Asana"
"What are the alternatives to Jira?"
"How much does Figma cost, and when was that price checked?"
"Find free password managers"
Related MCP server: IndieStack
Claude Code (hosted endpoint, nothing to install):
claude mcp add --transport http toolradar https://toolradar.com/api/mcpClaude Code plugin (the same server plus a skill that tells Claude when to use it):
claude plugin marketplace add Nadeus/toolradar-mcp
claude plugin install toolradar@toolradarClaude.ai, ChatGPT and other clients with custom connectors: add a remote MCP server with the URL https://toolradar.com/api/mcp (no authentication).
Claude Desktop, or any client that starts local servers (claude_desktop_config.json):
{
"mcpServers": {
"toolradar": {
"command": "npx",
"args": ["-y", "toolradar-mcp"]
}
}
}Cursor: use the button above, or Settings > MCP > add https://toolradar.com/api/mcp. VS Code: use the link above, or code --add-mcp '{"name":"toolradar","url":"https://toolradar.com/api/mcp"}'.
Tool | What it does | Example prompt |
| Reads a described need (category, team size, budget), returns a short list ordered by fit, with the reason, caveats and the verified starting price | "What should a 6-person agency use for a CRM under $40/mo?" |
| Keyword search; a category name ("crm", "password manager") or "alternative to X" returns that category's leaders or X's alternatives | "Find free project management tools" |
| Full profile: pricing, pros and cons, features, score, review synthesis | "Tell me about Linear" |
| Side-by-side comparison of 2-4 tools | "Compare Notion, ClickUp and Asana" |
| Direct competitors of a tool | "What are the alternatives to Jira?" |
| Tiers and prices with provenance: source page, verification date, confidence | "How much does Figma cost?" |
| The categories and how many tools each holds | "What categories are available?" |
| Report a wrong price, a dead tool or a missing feature to the verification queue | "Notion shows $8 but their site says $10" |
Every data answer includes a ready-to-use citation (Toolradar, verification date, link): quote it when you use the data.
Verified pricing: tiers read from the vendor's pricing page, with the date of the last check
Editorial score (0-100) and review ratings aggregated from review platforms
Pros, cons and features
Alternatives identified per tool, not just "same category"
Positions among tools of the same category, dated
Access | Calls per day |
Anonymous (nothing to configure) | 40 |
Free key, no signup: | 300 |
Key created in your dashboard | 1,000 |
Set the key in TOOLRADAR_API_KEY, or send it as Authorization: Bearer <key> to the hosted endpoint. Limits reset at 00:00 UTC.
Variable | Required | Default | Description |
| No | none | Raises the daily limit (see above) |
| No |
| Custom endpoint |
The npm package is a thin stdio proxy of the hosted endpoint, so both always return the same answers.
A nightly job asks the hosted endpoint 60 realistic software-choice questions (a full run of 205 every Sunday) and records how often a market leader of the category comes back in the top 3. The server is open for you to test.
toolradar.com/for-agents: landing page and examples
toolradar.com/docs: API documentation
npmjs.com/package/toolradar-mcp: npm package
plugin/ is one package for two directories: Claude Code (.claude-plugin/plugin.json, .mcp.json) and the OpenAI plugin format (plugin.json, mcp.json). Both carry the same skill (plugin/skills/toolradar/SKILL.md). The skill alone, for Claude Code:
claude skill add --url https://raw.githubusercontent.com/Nadeus/toolradar-mcp/main/skill-recommend-tool.mdCompare 2 to 4 software tools side by side. Returns structured comparison with pricing, scores, pros/cons, and computed insights (best overall, best value, most reviewed).
| Name | Required | Description | Default |
|---|---|---|---|
| slugs | Yes | Array of 2-4 tool slugs to compare (e.g. ['notion', 'clickup', 'asana']) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the return shape: pricing, scores, pros/cons, and computed insights. It does not discuss side effects or permissions, but for a read-only comparison tool this is adequate. Slightly more context on edge cases would push it to 5.
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, front-loaded with the core purpose, followed by the output details. No redundant words or filler. Every sentence 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 no output schema, the description is complete: it states what it does, the tool count range, and the key fields in the response. An agent has enough information to invoke it correctly without requiring additional clarification.
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 clear description for the 'slugs' parameter. The description reinforces the 2-4 range and tool context but adds no new syntax or format details beyond the schema. 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?
Description clearly states 'Compare 2 to 4 software tools side by side' with a specific verb and resource. It distinguishes from siblings like get_tool (single tool) and get_alternatives (alternatives rather than head-to-head comparison).
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?
Provides clear context: use when a side-by-side comparison of multiple tools is needed. It does not explicitly name alternatives or state when not to use it, but the purpose is clear enough for an agent to select it appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get alternatives and competitors for a specific software tool. Returns up to 10 alternatives sorted by editorial score.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Tool slug to find alternatives for (e.g. 'jira', 'slack') | |
| limit | No | Number of alternatives to return (default 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the return size limit ('up to 10') and sort order ('sorted by editorial score'), but it does not explicitly state that this is a read-only operation or mention any other behavioral traits like error handling or rate limits.
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 sentence that is concise and front-loaded. It efficiently conveys the core purpose and key output characteristics without any unnecessary words.
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 read-only listing tool with two well-documented parameters and no output schema, the description and schema together provide sufficient context. It covers the purpose, the return limit, and the sort order, making the tool's behavior predictable.
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 both 'slug' and 'limit' fully described in terms of type, constraints, and examples. The description adds little beyond the schema, only rephrasing the slug concept and the default limit, so 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 clearly states the action ('Get') and the resource ('alternatives and competitors for a specific software tool'), which distinguishes it from siblings like get_tool or search_tools. It precisely communicates the tool's purpose with no ambiguity.
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 this tool: when you need alternatives or competitors for a specific software product. It doesn't explicitly contrast with sibling tools like compare_tools, but the context is clear enough that an agent can infer the appropriate use case.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed pricing information for a software tool including tiers, pricing model (free/freemium/paid), free trial availability, and expert pricing verdict.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Tool slug (e.g. 'figma', 'github') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full transparency burden. It discloses the kinds of information returned (tiers, pricing model, trial, verdict), but lacks detail on behavior such as error handling for unknown slugs, response format, or whether authentication is required. This partial disclosure is acceptable but not comprehensive.
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 that efficiently conveys the tool's purpose and the key output categories. 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 single-parameter lookup, the description covers the main output areas effectively. However, the absence of an output schema makes the lack of explicit mention of edge cases (e.g., unknown slug behavior) or the return structure a minor gap. Overall, it is sufficiently complete for most use cases.
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 fully describes the sole parameter 'slug' with an example, achieving 100% schema coverage. The description adds no additional parameter-specific semantics, so the baseline score 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 clearly states that the tool retrieves detailed pricing information, listing specific content such as tiers, pricing model, free trial availability, and expert verdict. This effectively distinguishes it from sibling tools like get_tool or compare_tools by focusing uniquely on pricing details.
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?
Usage is implied rather than explicit. The description suggests using this tool when pricing information is needed, but it does not provide explicit guidance on when to prefer it over get_tool or other alternatives, nor does it mention 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.
Get detailed information about a specific software tool including description, pricing, pros/cons, features, editorial score, review synthesis, and alternatives.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Tool slug (e.g. 'notion', 'linear', 'figma'). Use search_tools first if you don't know the slug. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It clearly identifies a read-only lookup by using 'Get' and enumerates the response contents, but it does not address edge cases such as invalid slugs, error behavior, or whether any authentication is required. Still, for a simple retrieval tool, the behavioral profile is reasonably transparent.
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 well-structured sentence that front-loads the action and then lists what is included. No wasted words.
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?
The description effectively explains what data will be returned and indicates the need for a slug. It lacks explicit guidance on choosing between get_tool and the more specialized siblings, and has no output schema, but the one-parameter contract plus content list makes it mostly 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?
The input schema already has 100% coverage for the single slug parameter, including examples and guidance to use search_tools first. The tool description adds no parameter-level semantics beyond calling it 'a specific software tool', so the schema carries the 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?
The description uses a specific verb ('Get') and resource ('detailed information about a specific software tool') and enumerates the included fields. It does not explicitly distinguish this from siblings like get_pricing or get_alternatives, which overlap with the listed contents.
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 this is for retrieving details about a single known tool, but it does not provide explicit when/when-not guidance or mention sibling tools. The only usage hint ('Use search_tools first if you don't know the slug') lives in the schema parameter description, not in the tool description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all software categories available on Toolradar with tool counts. Use this to discover valid category slugs for the search_tools filter.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. It states the tool 'lists all software categories' and includes 'tool counts,' giving some insight into the output. However, it doesn't mention return format, pagination, or authentication requirements. For a 0-parameter read operation, this is adequate but not rich.
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 sentences, front-loaded with the primary action ('List all software categories'), and every word contributes meaning. No filler or redundant 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 0-parameter listing tool with no output schema, the description covers the essential points: it lists all categories, includes tool counts, and explains the intended purpose (discovering valid slugs). It doesn't mention ordering or response shape, but the simple nature of the tool makes this 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 tool has zero parameters, so the baseline is 4. The description doesn't need to explain parameters. It adds value by mentioning the tool counts and slug discovery purpose, which helps the agent understand the result's utility. Schema coverage is trivially 100%.
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's function: 'List all software categories available on Toolradar with tool counts.' It also specifies a distinct use case: 'Use this to discover valid category slugs for the search_tools filter,' which distinguishes it from sibling tools like search_tools and get_alternatives.
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 explicitly says to use this tool 'to discover valid category slugs for the search_tools filter,' providing clear context for when it's appropriate. It doesn't explicitly exclude other tools, but the intended usage is unambiguous and sufficient for a simple listing tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recommend the best software tools for a described need. Unlike search_tools (raw retrieval), this ranks candidates by fit, applies hard constraints (budget, pricing, category), and returns a justified, sourced shortlist with fit scores, caveats, verified starting prices, and next steps. Use this when a user asks 'what should I use for X'.
| Name | Required | Description | Default |
|---|---|---|---|
| need | Yes | Natural-language need, e.g. 'simple CRM for a 6-person agency that syncs with Gmail' | |
| limit | No | Number of recommendations (default 5, max 10) | |
| exclude | No | Tool slugs to exclude from the shortlist | |
| pricing | No | Restrict to a pricing model | |
| category | No | Restrict to a category slug (e.g. 'crm', 'project-management') | |
| team_size | No | Number of people who will use the tool | |
| max_monthly_budget | No | Hard cap on the per-tool monthly price in USD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It openly describes ranking by fit, enforcement of hard constraints, and the returned shortlist components: fit scores, caveats, verified starting prices, and next steps. It could disclose more about data sources or no-match behavior, but for a non-mutating recommendation tool this is substantial transparency.
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 purpose is front-loaded, the differentiation from search_tools is immediate, and the output characteristics are summarized without wasted words.
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?
Given that there is no output schema or annotations, the description does a good job covering what the tool returns and when to use it. It also conveys the ranking and constraint behavior. It does not cover edge cases like zero matching results or how to choose among the remaining siblings, but these are minor gaps.
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 each parameter. The description adds a useful high-level framing by identifying budget, pricing, and category as 'hard constraints' and mentioning fit-based ranking, but it does not add significant per-parameter semantic detail beyond what the schema provides.
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 ('Recommend'), a clear resource ('software tools'), and a clear purpose ('for a described need'). It also explicitly contrasts itself with search_tools ('Unlike search_tools (raw retrieval)'), so an agent can distinguish it from a key sibling 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?
Provides an explicit usage trigger: 'Use this when a user asks "what should I use for X"' and explains how it differs from search_tools. However, it does not address when to prefer other siblings like compare_tools, get_alternatives, or get_pricing, so there is no full exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Report a data-quality issue you spotted while using Toolradar data (a wrong price, a dead/renamed tool, a missing or incorrect feature). Files a ticket to the verification queue. Use this when Toolradar data contradicts what you observe on the vendor's own site.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Tool slug the issue is about (e.g. 'notion') | |
| claim | Yes | What is incorrect and what it should be, in one or two sentences | |
| field | No | What is wrong (default 'other') | |
| evidence_url | No | A URL backing the claim (ideally the vendor's own page) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It reveals the key side effect: 'Files a ticket to the verification queue,' clarifying that the tool does not directly edit data but queues it for review. This is meaningful context beyond the schema, though other potential behaviors (e.g., auth requirements, response format) are not addressed.
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 efficient: two sentences that front-load the purpose, provide concrete examples, and state the usage condition. There is no filler or redundant restating of schema fields.
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 relatively simple four-parameter tool with 100% schema coverage, the description covers purpose, usage condition, and the core behavioral outcome (verification queue ticket). It does not describe the response/return value, but the schema and the 'files a ticket' statement provide enough context for correct invocation. Slightly more detail about what happens after filing would make it completely self-contained.
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. The description adds extra semantic value by mapping issue examples to the field enum ('wrong price' → pricing, 'dead/renamed tool' → status, 'missing or incorrect feature' → feature) and by referencing evidence from the vendor's own site, which aligns with the evidence_url parameter.
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's purpose: 'Report a data-quality issue' with concrete examples ('wrong price, dead/renamed tool, missing or incorrect feature'). It also identifies the resource (Toolradar data) and differentiates from sibling tools that search, compare, or list tools, none of which handle issue reporting.
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 an explicit when-to-use condition: 'Use this when Toolradar data contradicts what you observe on the vendor's own site.' It does not explicitly name alternatives or state when not to use the tool, but the condition is clear and the sibling tools are functionally distinct enough that an agent can route correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search and filter software tools from Toolradar's database of 8,600+ tools. Returns tools with names, descriptions, pricing, scores, and categories.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Sort order: score (editorial rating), recent (newest first), rating (user review rating) | |
| limit | No | Number of results (default 10, max 50) | |
| query | No | Search query (e.g. 'project management', 'AI writing tool') | |
| pricing | No | Filter by pricing model | |
| category | No | Filter by category slug (e.g. 'project-management', 'ai-writing') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It adds useful context by stating the database scale and returned fields, implying a read-only operation, but it does not explicitly confirm absence of side effects, auth requirements, or rate limits. For a search tool this is a mild gap, not a serious one.
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 first identifies the action and scope, the second lists output fields. It is front-loaded with the verb and every sentence 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?
With a fully documented schema and no output schema, the description adequately covers the tool's function and return fields. It could be slightly richer by noting that all parameters are optional or mentioning default sort behavior, but those are already implied by the schema, so the definition is complete enough for correct invocation.
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 documents all 5 parameters with 100% coverage, including enum values, min/max, and examples. The description adds no parameter-level detail, which is acceptable because the schema does the heavy lifting; baseline 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 states a specific verb and resource — 'Search and filter software tools from Toolradar's database' — and lists return fields, making the purpose clear. It does not explicitly differentiate from siblings like recommend_tools or compare_tools, but the search/filter framing is distinct enough for basic disambiguation.
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 guidance on when to use this tool versus alternatives such as recommend_tools, get_tool, or compare_tools. The description only states what the tool does, leaving the agent to infer the intended use case from the name and sibling list.
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.
v2.1.1recommend_toolsreport_issuesearch_tools2 fields changedInput schema / properties / sort / descriptionPrevious value: -"Sort order: score (editorial rating), recent (newest), trending (most upvotes this week)"New value: +"Sort order: score (editorial rating), recent (newest first), rating (user review rating)"Input schema / properties / sort / enumPrevious value: -[
- "score",
- "recent",
- "trending"
-]New value: +[
+ "score",
+ "recent",
+ "rating"
+]v1.0.1compare_toolsget_alternativesget_pricingget_toollist_categoriessearch_toolsScored across 8 tools
Most tools have a clearly distinct purpose: search, recommend, compare, get details, get pricing, etc. However, get_tool already includes pricing, alternatives, and review synthesis, creating some overlap with get_pricing and get_alternatives; the descriptions mitigate this but do not fully eliminate ambiguity.
All tool names follow a consistent verb_noun snake_case pattern (recommend_tools, search_tools, get_tool, list_categories, report_issue). The verbs are simple and predictable, making the toolset easy for an agent to navigate.
Eight tools is well-scoped for a software discovery database. Each tool earns its place by covering a distinct step in the workflow: browsing categories, searching, getting details, comparing, finding alternatives, checking pricing, getting recommendations, and reporting data issues.
The tool surface covers the full discovery workflow with no obvious dead ends: discover categories, search, retrieve details, compare, find alternatives, get pricing, and receive recommendations. The report_issue tool also provides a feedback loop for data quality, which is a thoughtful completion of the domain.
Curated directory of AI software: search tools, read listings, compare tools.
Search 2,000+ AI tools: pricing, alternatives, comparisons, and live, dead or acquired status.
Search and compare 4,700+ AI tools: pricing, features, alternatives. Free, no API key.
Independent directory of agentic AI tools — search, compare & recommend via MCP. Read-only.
