Skip to main content
Glama

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, the date our record of it was last rebuilt, 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
NameRequiredDescriptionDefault
needYesWhat the tool must do, in the user's own words. e.g. "transcribe podcast interviews with speaker labels".
limitNoHow many results to return (max 10).
requires_apiNoOnly return tools recorded as offering an API.
survival_barNoexclude_at_risk = drop tools scoring below the at-risk threshold, with a failing main site, or whose published website now redirects to a different company. safe_bet_only = only the strongest band. none = no survival screening (moved-identity tools are then returned WITH the move stated).exclude_at_risk
pricing_modelNoFilter 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_wrappersNoExclude tools assessed as thin wrappers around a third-party model.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / survival_bar / description
      Previous value: -"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."New value: +"exclude_at_risk = drop tools scoring below the at-risk threshold, with a failing main site, or whose published website now redirects to a different company. safe_bet_only = only the strongest band. none = no survival screening (moved-identity tools are then returned WITH the move stated)."
  2. Added

TDQS

A4.4/5.0
Behavior3/5

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

Annotations (readOnlyHint=true, destructiveHint=false, openWorldHint=false) already declare this is a safe, closed-world read. The description goes well beyond them by disclosing survival screening mechanics (link-health probes, 5-signal viability model), the separate listing of unmeasured tools, and the response contents (health verdict, record rebuild date, pricing model). However, it does not cover pagination, ordering, or how fuzzy-match confidence is surfaced.

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?

Long but densely front-loaded: the trigger condition comes first, then return shape, then the 'Not for' routing. Every sentence carries routing or behavioral information; the length is justified by the number of decision points, though it is near the upper bound of what an agent will parse comfortably.

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?

No output schema exists, and the description compensates fully by describing the response (shortlist matched on need plus constraints, per-result health verdict, rebuild date, pricing model, CTA that the matching method is keyword/fuzzy). With 6 params and 2 enums, nothing an agent needs to call correctly is missing.

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 baseline is 3, but the description adds real meaning beyond the schema: it explains what survival_bar=exclude_at_risk actually drops (below-threshold scores, failing main site, redirected domain) and why no price-amount filter exists. These enrich the enum semantics rather than restating them.

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?

States a specific verb+resource (recommend AI tools for a described need) and immediately frames the distinguishing condition — user describes a job, not a named tool. It also names the sibling tools it is not (check_tool_status, compare_tools), so an agent can route without opening another schema.

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?

Explicit 'use this when' trigger is given with concrete example phrasings, plus a 'Not for:' clause naming two alternatives and the exact condition that selects each. The price-amount exclusion is also stated as a hard boundary.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources