Skip to main content
Glama

agentery

by com.agentery
OverviewDiscussionsAdmin

research_capability

Optional combined research route: ONE call turns a task into: (1) its live MARKET — the semantic neighbourhood of the closest-matching providers, found purely by text-embedding nearness (NO fixed category), with the relevance floor and how many providers cleared it; (2) current pricing context — comparable price range and median with mean, stdev and n, plus provider/priced counts; and (3) a ready-to-compare provider shortlist — each with observed price, market_position (below/in-line/above market), integration status, match score, and handles collected in compare_ready. Retrieval is 100% nearest-neighbour by text embedding: providers are matched on what they actually DO, never on an assigned label. REUSES the canonical pricing/search engines (no new pricing logic). Also returns suggested_alternatives (cheaper or stronger options) and a result_fingerprint (+ cached) so repeat calls are cheap. It does NOT run the comparison — pass compare_ready to compare_providers once you have finalists. For detailed inspection prefer the default path: search_providers → get_provider_profile → compare_providers. Aliases: task also accepts query / q.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoShortlist ordering. Default 'match'.
taskYesRequired — the natural-language capability/task, e.g. 'reconcile supplier invoices' or 'litigation-analysis provider'. Aliases: query, q.
limitNoShortlist size (1-12, default 5).
buyer_tierNoOptional buyer tier to price against ('team' = Team/SME).
integrationsNoOptional required integrations, e.g. ["zendesk","slack"] — soft preference; integration status is reported per provider.
provider_typeNoPreferred delivery type. 'auto' (default) infers from the task; note 'AI agent' phrasing is treated as generic (neutral), not an agent-only filter. When a type is explicit (mcp/api/agent) matching providers are SOFT-RANKED to the top and the rest are kept as clearly-labelled cross_type_alternative entries — never hard-filtered (no zero-result cliff), and the functional match is never changed. Every provider is labelled with provider_type (public values: agent | mcp | api | unknown) + type_match_score; provider_type{type_rank_boost_applied, boosted_provider_type, result_counts_by_type} is returned.
response_modeNo'summary' (default) or 'full' (adds tier cohorts, coverage and raw results).
max_monthly_usdNoOptional budget ceiling in USD/month — filters the shortlist and drives suggested_alternatives.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / provider_type / enum
      Previous value: -[
-  "auto",
-  "provider",
-  "mcp",
-  "api",
-  "any"
-]New value: +[
+  "auto",
+  "agent",
+  "mcp",
+  "api",
+  "any"
+]
  2. Changed1 schema field changed
    • changedInput schema / properties / provider_type / description
      Previous value: -"Preferred delivery type. 'auto' (default) infers from the task; note 'AI agent' phrasing is treated as generic (neutral), not an agent-only filter. When a type is explicit (mcp/api/agent) matching providers are SOFT-RANKED to the top and the rest are kept as clearly-labelled cross_type_alternative entries — never hard-filtered (no zero-result cliff), and the functional niche is never changed. Every provider is labelled with provider_type (public values: agent | mcp | api | unknown) + type_match_score; provider_type{type_rank_boost_applied, boosted_provider_type, result_counts_by_type} is returned."New value: +"Preferred delivery type. 'auto' (default) infers from the task; note 'AI agent' phrasing is treated as generic (neutral), not an agent-only filter. When a type is explicit (mcp/api/agent) matching providers are SOFT-RANKED to the top and the rest are kept as clearly-labelled cross_type_alternative entries — never hard-filtered (no zero-result cliff), and the functional match is never changed. Every provider is labelled with provider_type (public values: agent | mcp | api | unknown) + type_match_score; provider_type{type_rank_boost_applied, boosted_provider_type, result_counts_by_type} is returned."
  3. Changed2 schema fields changed
    • changedInput schema / properties / provider_type / enum
      Previous value: -[
-  "auto",
-  "agent",
-  "mcp",
-  "api",
-  "any"
-]New value: +[
+  "auto",
+  "provider",
+  "mcp",
+  "api",
+  "any"
+]
    • changedInput schema / properties / task / description
      Previous value: -"Required — the natural-language capability/task, e.g. 'reconcile supplier invoices' or 'litigation-analysis agent'. Aliases: query, q."New value: +"Required — the natural-language capability/task, e.g. 'reconcile supplier invoices' or 'litigation-analysis provider'. Aliases: query, q."
  4. Changed1 schema field changed
    • changedInput schema / properties / provider_type / description
      Previous value: -"Preferred delivery type. 'auto' (default) infers from the task; note 'AI agent' phrasing is treated as generic, not an agent-only filter. Every provider is labelled with entity_type and result_counts_by_type is returned."New value: +"Preferred delivery type. 'auto' (default) infers from the task; note 'AI agent' phrasing is treated as generic (neutral), not an agent-only filter. When a type is explicit (mcp/api/agent) matching providers are SOFT-RANKED to the top and the rest are kept as clearly-labelled cross_type_alternative entries — never hard-filtered (no zero-result cliff), and the functional niche is never changed. Every provider is labelled with provider_type (public values: agent | mcp | api | unknown) + type_match_score; provider_type{type_rank_boost_applied, boosted_provider_type, result_counts_by_type} is returned."
  5. Changed1 schema field changed
    • addedInput schema / properties / provider_type
      Added value: +{
+  "description": "Preferred delivery type. 'auto' (default) infers from the task; note 'AI agent' phrasing is treated as generic, not an agent-only filter. Every provider is labelled with entity_type and result_counts_by_type is returned.",
+  "enum": [
+    "auto",
+    "agent",
+    "mcp",
+    "api",
+    "any"
+  ],
+  "type": "string"
+}
  6. Added

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries most of the behavioral burden. It discloses the retrieval method (100% nearest-neighbour embedding, no fixed category), the reuse of existing pricing/search engines, caching behavior via result_fingerprint, and the explicit negative that it does not run comparisons. It stops short of stating read-only status or any auth/rate-limit constraints, but is still substantive.

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 dense and well-structured with enumerated result components, bolded caveats, and front-loaded purpose. It is somewhat long and repeats alias details already in the schema, but most sentences earn their place by conveying routing or behavioral constraints.

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?

Given the tool's complexity — 8 parameters, 4 enums, and no output schema — the description is remarkably complete. It enumerates the main outputs (market, pricing stats, compare_ready shortlist, suggested_alternatives, fingerprint/cached), explains retrieval semantics, and provides the recommended fallback path, giving an agent enough context to call it effectively.

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

Parameters3/5

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 all 8 parameters, including enums and defaults. The description adds output-oriented context and repeats the task alias already present in the schema, but does not materially enrich parameter meaning beyond what the input schema provides.

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 names a specific combined action: 'ONE call turns a task into' a live market, pricing context, and compare-ready shortlist. It also distinguishes the tool from siblings by explicitly stating it does NOT run the comparison and reuses the canonical pricing/search engines rather than adding new logic.

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 states when not to use it ('It does NOT run the comparison'), what to do instead ('pass compare_ready to compare_providers once you have finalists'), and the preferred detailed-inspection path ('search_providers → get_provider_profile → compare_providers'). This gives concrete when-to/when-not routing guidance.

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

All agentery toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources