Search Fragments

Submit Resolution Feedback

submit_resolution_feedback

After the user reacts to a resolve_fragment result, call this with its resolution_id. accepted: it is what they meant. partial: it helped but is not quite it. rejected: it is not what they meant. If they recognised an item in the shortlist or leads, send picked_rank (1 = first item) or picked_url; if nothing fitted, send none_fitted: true. corrected_target and new_clue are optional and are stored as feedback only; they never change graph facts.

Input Schema

Name	Required	Description
`note`	No	Optional free-text note. Max 1000 characters. No personal data.
`status`	Yes	accepted: the result is what the user meant. partial: it helped but is not quite it. rejected: it is not what the user meant.
`new_clue`	No	Optional. An extra detail the user remembered after seeing the result. Max 500 characters.
`picked_url`	No	URL of the item the user recognised.
`none_fitted`	No	True if the user looked and nothing fitted.
`picked_rank`	No	Position of the shortlist or lead item the user recognised.
`resolution_id`	Yes	The resolution_id returned by the resolve_fragment call this feedback is about.
`corrected_target`	No	Optional. What the user was actually thinking of, if they know it. Max 300 characters.

Output Schema

Name	Required	Description	Default
`status`	Yes
`recorded`	Yes
`resolution_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 20, 2026

addedInput schema / properties / none_fitted

Added value: +{
+  "description": "True if the user looked and nothing fitted.",
+  "type": "boolean"
+}

addedInput schema / properties / picked_rank

Added value: +{
+  "description": "Position of the shortlist or lead item the user recognised.",
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / picked_url

Added value: +{
+  "description": "URL of the item the user recognised.",
+  "type": "string"
+}

Changed5 schema fields changedSep 29, 2026

addedInput schema / properties / corrected_target / description

Added value: +"Optional. What the user was actually thinking of, if they know it. Max 300 characters."

addedInput schema / properties / new_clue / description

Added value: +"Optional. An extra detail the user remembered after seeing the result. Max 500 characters."

addedInput schema / properties / note / description

Added value: +"Optional free-text note. Max 1000 characters. No personal data."

addedInput schema / properties / resolution_id / description

Added value: +"The resolution_id returned by the resolve_fragment call this feedback is about."

addedInput schema / properties / status / description

Added value: +"accepted: the result is what the user meant. partial: it helped but is not quite it. rejected: it is not what the user meant."

AddedSep 20, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description adds genuinely new behavior: corrected_target and new_clue are 'stored as feedback only; they never change graph facts,' which tells the agent this is a safe, non-mutating-in-effect write. Rate limits, permissions, or what happens on an unknown resolution_id are not covered.

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 when-to-call clause is front-loaded and every sentence maps to a decision the caller must make. It is dense but earns its length; minor duplication of the status definitions that also appear in the schema.

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

Completeness4/5

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

With 8 parameters, a mutation annotation profile, and an output schema (so return values need no explanation), the description covers trigger, parameter selection, and side effects. Only edge cases such as invalid or stale resolution_id handling are 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 baseline is 3, but the description goes further by explaining the choice logic among picked_rank ('1 = first item'), picked_url, and none_fitted, and by tying status values to observed user reactions. It adds meaning beyond the schema text rather than repeating it.

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 action (submit feedback with the resolution_id from a resolve_fragment result) and ties it to the exact sibling that produces that ID, so it is distinguishable from resolve_fragment and verify_claim without reading a schema.

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

Usage Guidelines4/5

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

It states the trigger condition precisely ('After the user reacts to a resolve_fragment result') and gives per-case guidance for status and for the shortlist/leads outcomes. It does not say when not to call or what to do if no prior resolution exists, so it falls short of a full 5.

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

All Search Fragments tools Inspect

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.