Search Fragments
Server Details
For queries a model can't confidently place: resolves or declines. Never a confident-wrong.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.9/5 across 1 of 1 tools scored.
With only one tool, there is no possibility of confusion. The tool's purpose is uniquely defined and distinct from any other tool in the server.
With a single tool, naming consistency is perfect. The name 'resolve_fragment' clearly conveys its function.
The server has one tool, which is slightly below the typical range of 3-15 for a well-scoped server, but the tool is highly specialized and earns its place for the specific niche of resolving vague queries.
The tool covers the entire domain of resolving half-remembered queries, providing multiple result types and clearly stating its limitations. There are no obvious gaps for its stated purpose.
Available Tools
1 toolresolve_fragmentARead-onlyInspect
For the queries a model can't confidently place — half-remembered, cross-source, 'I know this exists but can't name it' — where an agent would otherwise guess and risk a confident-wrong. Search Fragments resolves the real answer, returns a ranked shortlist of sources to assemble, or an explicit 'not resolvable from text.' It never asserts a confident answer — every result is decide-by-eye with a confidence level. In a 50-fragment test on hard, under-documented queries, a baseline agent invented specific answers — a nonexistent Japanese director, a Ronnie Barker sketch that was never performed, a study attributed to a geneticist who never published it. Search Fragments declined honestly on all three. Not for direct or single-fact lookups — a normal search is faster for those.
Examples:
a musician who became famous largely for stopping performing
somebody who photographed the same view every day until the changes became the artwork
a song everybody knew but nobody could identify
the company that bought Instagram before it was big
a novel where the footnotes slowly become the real story
Not for:
what is the capital of France
who directed Jaws
name of french artist cubist painting 1948
| Name | Required | Description | Default |
|---|---|---|---|
| fragment | Yes | The half-remembered or fragment-shaped query, in the user's own words. Should be at least 5 words and describe the thing being recalled by premise, plot, relationship, or context. |
Output Schema
| Name | Required | Description |
|---|---|---|
| pool | Yes | Ranked web results. Always DECIDE-BY-EYE — human must confirm before any graph write. |
| outcome | Yes | 'resolved' = strong candidate identified (semantic pass returned high/medium confidence title). 'ranked_stalls' = web results returned but no confident semantic identification — pool for human review. 'no_resolution' = not an SF question, or pipeline produced an empty pool. |
| candidate | Yes | Top candidate when outcome=resolved; null otherwise. DECIDE-BY-EYE — human must confirm. |
| reject_reason | Yes | Why the fragment was rejected; non-null only when is_sf_question=false. |
| is_sf_question | Yes | true if the fragment is a valid memory-recall query; false if it was rejected as a direct lookup or research prompt. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly and openWorld hints. The description adds critical behavioral details: it never asserts a confident answer, returns results with confidence levels for human review, and includes a real-world test showing honest refusal on ambiguous queries.
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 well-structured with a clear opening, followed by examples and exclusions. Every sentence contributes meaningful information, and the text is front-loaded with the tool's core purpose.
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 the single parameter, no sibling tools, and presence of annotations and output schema, the description provides complete context: purpose, usage guidelines, behavioral traits, and parameter semantics.
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%, but the description adds value by specifying minimum word length (at least 5) and the type of content expected (premise, plot, relationship, or context), going beyond the schema's description.
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 resolves fragmentary queries and returns ranked sources or an explicit 'not resolvable,' distinguishing it from a normal search. Examples of appropriate and inappropriate queries reinforce its specific purpose.
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?
Explicitly describes when to use (half-remembered, cross-source queries) and when not to (direct single-fact lookups), with clear examples of both appropriate and inappropriate use cases, including an explicit alternative (normal search).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!