Skip to main content
Glama

graviti

by ai.thesingulariti

Match buyer intent to brands

match_intent
Read-onlyIdempotent

Takes a natural-language buyer question plus optional intent profile; returns recommendations ranked purely by fit score. Verification status is disclosed but never affects rank. Questions outside the verified index return an explicit out-of-scope result (in_index: false), never a guess. Brands without captured evidence (catalog_only) are returned in in_landscape_not_evidenced — listed, never scored, never recommended. Each recommendation carries the brand's site link twice: site_url (raw) and attributed_url (tagged utm_source=graviti + a signed gvt token, so the brand can verify the referral — surface-level only, no user data). Prefer attributed_url when linking.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYesThe buyer's question, as they phrased it
intent_profileNoBuyer intent voice; inferred from the question if omitted

TDQS

A4.1/5.0
Behavior5/5

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

The description goes well beyond the annotations, revealing that verification status is disclosed but never affects rank, out-of-scope questions return in_index:false instead of guesses, and catalog_only brands are never scored or recommended. It also explains the URL attribution behavior and explicitly notes that no user data is included, giving an agent a strong mental model of the tool's behavior.

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

Conciseness5/5

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

The description is front-loaded with the primary purpose and then adds dense, high-value behavioral detail without filler. Every sentence provides actionable information for selecting or invoking the tool correctly.

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 covers key return fields and edge cases: in_index, in_landscape_not_evidenced, site_url, attributed_url, and recommendation ranking behavior. This is sufficient context for an agent to understand what the tool returns and how to handle the two main non-standard cases.

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 both parameters well. The description adds minimal extra parameter meaning beyond clarifying that the question is natural language and the intent profile is optional.

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

Purpose4/5

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

The description clearly states the tool's verb and resource: it takes a natural-language buyer question and returns brand recommendations ranked by fit score. It doesn't explicitly differentiate from sibling tools by name, but the behavior described is distinct enough to make the tool's purpose clear.

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

Usage Guidelines3/5

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

Usage is implied: the tool should be used when you have a natural-language buyer question and want brand recommendations ranked by fit score. However, it never explicitly states when to prefer this tool over alternatives or mentions any of the sibling tools.

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

All graviti toolsInspect
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

A4.2/5.0
Disambiguation4/5

Each tool targets a distinct resource: category comparisons, verified claims, gap analysis, intent matching, conversion logging, accountability events, and the index ledger. The only mild ambiguity is between category_landscape and match_intent, or between get_accountability_log and get_ledger, but the descriptions draw clear boundaries.

Naming Consistency4/5

Most read operations follow a clean get_ pattern, and the action tools use verb_noun naming. category_landscape deviates as a bare noun phrase, which is the main inconsistency, but overall the names remain readable and predictable.

Tool Count5/5

Seven tools is well-scoped for this domain: consumers can discover brands, inspect evidence, evaluate gaps, audit integrity, and record conversions without redundant operations or missing categories.

Completeness4/5

The set covers the core workflows: discovery, verification lookup, gap analysis, audit/log integrity, and conversion attribution. There are minor gaps—no direct tool to create or update claims—but agents can accomplish the intended consumer-facing tasks without dead ends.

Resources