RightAIChoice

Find an AI tool for a job — that will still exist next year

recommend_tools

Read-only

Use this when the user describes what they need an AI tool to DO rather than naming one — "something to transcribe interviews", "an image generator with an API", "a writing tool for a small team". Returns a verified shortlist matched on the described need, filtered by constraints the caller sets, and — unique to this catalog — screened against a survival bar: tools failing our link-health probes or scoring badly on the 5-signal viability model can be excluded outright. Each result carries its own health verdict, last-verified date and pricing model. Matching is keyword and fuzzy text search over 8,000+ verified tools; the response states this. Tools with no viability measurement yet are listed separately by name rather than silently dropped. Not for: questions about a tool the user already named (use check_tool_status), head-to-head choices (use compare_tools), or filtering by price amount — prices are recorded verbatim in mixed currencies and are never converted or compared numerically.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`need`	Yes	What the tool must do, in the user's own words. e.g. "transcribe podcast interviews with speaker labels".
`limit`	No	How many results to return (max 10).
`requires_api`	No	Only return tools recorded as offering an API.
`survival_bar`	No	exclude_at_risk = drop tools scoring below the at-risk threshold or with a failing main site. safe_bet_only = only the strongest band. none = no survival screening.	exclude_at_risk
`pricing_model`	No	Filter by recorded pricing model. has_free_option = free or freemium. There is no price-amount filter: prices are verbatim strings in mixed currencies.	any
`exclude_wrappers`	No	Exclude tools assessed as thin wrappers around a third-party model.

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as read-only and non-destructive, and the description adds meaningful behavioral context: keyword/fuzzy search over 8,000+ tools, survival screening via link-health probes and a 5-signal model, and separate listing of unmeasured tools rather than silently dropping them. This aligns with the annotations, and the closed list of verified tools is consistent with openWorldHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the primary use case and organized with a clear "Not for" section. It is somewhat dense and repeats the word "verified" a couple of times, but every sentence contributes meaningful guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description explains what the response contains (shortlist, health verdict, last-verified date, pricing model), how matching works, and how edge cases like unmeasured tools are handled. The sibling-routing exclusions also make the tool safe to select in context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema documents all six parameters well. The description still adds value by explaining the survival_bar mechanism, the verbatim/mixed-currency nature of pricing, and the no-price-amount-filter constraint, helping an agent reason about parameter behavior beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action and resource: find AI tools matching a user's described need, returning a verified shortlist. It also explicitly differentiates from siblings by saying what it is not for: questions about a named tool, head-to-head comparison, or price-amount filtering.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear trigger condition: use when the user describes what a tool should DO rather than naming one. It also names alternatives explicitly — check_tool_status for named tools and compare_tools for comparisons — and explains when not to use it, including price-amount filtering.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All RightAIChoice tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation3/5

Most tools split cleanly by question shape (single-tool vs pair vs category vs market), but check_tool_status overlaps heavily with viability_score, market_sentiment, and pricing_reality by bundling the same evidence into one verdict. The extensive not-for cross-references help an agent route, yet several boundary cases like 'is this safe to adopt?' could reasonably go to multiple tools.

Naming Consistency3/5

The names are all readable lowercase snake_case, but they mix verb-led names (check_tool_status, compare_tools, find_alternatives, recommend_tools) with noun-phrase names (category_landscape, market_sentiment, pricing_reality, viability_score), and whats_changed follows neither pattern. There is no single consistent verb_noun convention, though the style is still predictable enough to be browsable.

Tool Count5/5

Ten tools is an appropriate size for a domain covering single-tool research, pairwise comparison, recommendations, alternatives, and aggregate market statistics. Each tool has a reasonably narrow slice of responsibility, so none feel redundant or like filler.

Completeness5/5

The set covers the key query lifecycle for AI-tool intelligence: liveness, viability, sentiment, pricing, change history, comparisons, alternatives, recommendations, category health, and market mortality. Cross-references between tools prevent dead ends, and the only notable limitations are explicitly disclosed rather than silently missing.

Resources

Need Help?