TraceDelta
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_investigationA | Begin (or reuse) a bounded production investigation. |
| find_related_capsulesA | Find existing capsules matching a service/environment/symptom/time window. Returns candidates and the reason for the match. Never merges automatically. |
| get_capsuleC | Fetch a capsule: situation, typed claims (facts / comparisons / correlations / hypotheses / known-unknowns / action-candidates), evidence references, freshness, and consumers. Respects the capsule's redaction policy. |
| refresh_capsuleC | Return only what CHANGED since the latest capsule version (a delta), not a reprint. Re-queries the backend for the minimum needed and creates a new version. |
| verify_claimA | Show the supporting and contradicting source evidence for one claim, with the exact query fingerprint, source time range, and deep link. Use to challenge an answer. |
| drill_downC | Retrieve the bounded raw evidence behind a reference (redacted, field-limited). This is the explicit cost path; the response reports estimated source bytes examined. |
| compare_capsulesC | Structured difference between two capsule versions. Does not infer causality. |
| report_savingsC | Estimated avoided work: capsule reuse, duplicate source queries avoided, source bytes vs response bytes (context compression), and a labelled token-savings estimate. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a distinct operation in the investigation workflow: starting an investigation, finding related capsules, fetching a capsule, diffing versions, computing deltas, verifying a claim, drilling into raw evidence, and reporting savings. The purposes are clearly separable with no meaningful overlap.
Names use a consistent verb_noun convention (start_investigation, get_capsule, compare_capsules, verify_claim, report_savings). Slight variation exists (drill_down is verb_adverb, refresh_capsule/report_savings are slightly different patterns), but overall the style is coherent and predictable.
Eight tools is well within the ideal range and each earns its place by covering a distinct phase of the investigation lifecycle: creation, discovery, retrieval, comparison, refresh, verification, detail, and reporting. No filler or redundant tools.
The surface covers the full epistemological loop: start an investigation, find existing related work, retrieve details, compare versions, refresh for changes, verify claims with raw evidence, drill down into source references, and report on savings. There are no dead ends or obvious missing operations for the stated domain.