fahali-mcp

fahali_get_watch_delta

Return only changes for a persistent monitor-only watch—verdict IDs, risk shifts, threshold crossings, and new evidence—so unchanged results are explicit and do not imply trading safety.

Instructions

Return only what changed for a persistent monitor-only watch: escalation label, risk band, direction, evidence coverage, threshold crossings, new evidence, and previous/current immutable verdict IDs. Defaults to a fresh evaluation. An unchanged result is explicit and never interpreted as market safety or permission to trade.

Input Schema

Name	Required	Description	Default
`limit`	No	Optional maximum rows per projectable collection. Audit has no MCP projection cap; brief defaults to 3 and standard to 12.
`since`	No	Optional lower timestamp bound for returned row collections.
`detail`	No	Response depth. audit is the full-fidelity default; brief and standard are explicit compact projections.	audit
`refresh`	No	True re-evaluates and may persist a new verdict (requires write:portfolio). False compares stored verdicts only (read:portfolio).
`symbols`	No	Optional symbol projection, as a comma-separated string or array. Rows without instrument identity are not discarded.
`watch_id`	Yes
`include_withheld`	No	Include full withheld-row detail. Defaults true with audit; explicitly set false only for a compact projection.

Output Schema

Name	Required	Description
`asOf`	No
`auth`	No	Credential lifetime visible to the caller. OAuth secondsRemaining lets an autonomous agent refresh before a multi-call workflow is interrupted.
`claim`	No	Fahali dictionary claim (shared/fahaliDictionary.ts). Read `kind` FIRST: 'abstention' means no assertion was made and `reason` says why — never read an abstention as a neutral or zero result. `basis` says what the claim rests on. Absent or null means this response path does not yet emit a claim; treat that as unknown, not as agreement.
`delta`	No
`items`	No
`scope`	No
`watch`	No
`status`	Yes
`absence`	No	Why no actionable finding is present: measured_empty, user_empty, no_coverage, source_unverified, stale, withheld, source_error, auth_failure, or entitlement_required.
`verdict`	No
`watches`	No
`decision`	No
`conflicts`	No
`dataState`	Yes
`mcpStatus`	No	Normalized MCP result status. The endpoint's original status vocabulary remains in `status` and `sourceStatus`.
`refreshed`	No
`requestId`	No
`verdictId`	No
`nextCursor`	No
`validUntil`	No
`claimPolicy`	No	Typed constraints for safe use. Metadata, not a prompt or instruction channel.
`idempotency`	No
`instruments`	No	Resolved or explicitly partial instrument identities. A missing venue carries an ambiguity warning.
`nextActions`	No	Registry-validated follow-up calls. Missing tools, invalid arguments, unresolved placeholders, and disabled tools are omitted.
`sourceError`	No	The upstream endpoint's exact error text/code before normalization, when one was present.
`sourceScope`	No
`decisionHash`	No
`evidenceHash`	No
`sourceStatus`	No	The upstream endpoint's exact status before the MCP envelope normalizes transport success/error.
`subscription`	No
`agentBriefing`	No	Audit-only narrative projection. Present only when detail='audit'; compact responses do not duplicate structured data as prose.
`claimValidity`	No	Validity of the selected binding claim only, calculated after filtering, projection and row selection. Sibling rows cannot determine it.
`operatingMode`	Yes
`responseState`	No
`schemaVersion`	No
`signingSecret`	No
`subscriptions`	No
`authorityState`	No
`sourceDecision`	No
`symbolCoverage`	No	Conservation ledger satisfying requested = returned + withheld + notReturned for requested-symbol calls.
`evidenceQuality`	No
`responseControl`	No
`sourceDataState`	No	The upstream endpoint's exact data-state value before endpoint-aware classification.
`evidenceSnapshot`	No	Compact immutable source snapshot needed to verify evidenceRef integrity on delta responses.
`recordMatchReason`	No	Why matchedTrackRecord is present or null. A null record is never evidence of safety or engine failure.
`signingSecretNote`	No
`matchedTrackRecord`	No	A judged record only when engine, horizon, regime/instrument class, and claim family match this response. `state` is one of: `measured` (a stratum cleared the publishability gate — `stratum` carries engine, horizon tier, bar regime, recall, precision, base rate, base-rate lift, median lead hours, effective sample, warned events and the measurement date); `withheld` (the gate ran and refused — `reason` says why, in words); `unavailable` (the record could not be read at all — an infrastructure failure that says nothing about the record). It is ONE stratum selected by recall, never a platform-wide accuracy. Null means no exact record match; read recordMatchReason.
`methodologyVersion`	No
`confidenceSemantics`	No	Every confidence-bearing value with its score type, scale, calibration status, and probability flag.
`decisionEligibility`	No	Fail-closed binding-authority policy. WITHHELD means source evidence remains available for audit while normalized direction, actionability and execution fields are revoked.
`directionEligibility`	No	Current market-direction eligibility. Direction is authorized only by an exact, eligible producer stratum (canonical_verdict, canonical_symbol_verdict, committee_verdict) — read bindingAuthority to see which one bound. Widening WHO may bind did not weaken WHAT binding requires: the named producer must still hold a matching horizon/class/family record on a verified-only judged population, so an authority without a record still cannot bind.
`executionEligibility`	No	Fail-closed execution boundary. Portfolio monitoring tools always return WITHHELD with MONITOR_ONLY_NO_EXECUTION_AUTHORITY while Fahali has no capital path.
`legacyFieldSemantics`	Yes
`outputClassification`	Yes
`monitoringEligibility`	No	Current portfolio-monitoring validity based on captured identity, freshness, integrity, and the caller-supplied monitoring policy. ELIGIBLE authorizes observation/delivery only, never financial action.
`sourceEvidenceQuality`	No
`currentActionEligibility`	No	Current eligibility of an immutable historical portfolio verdict. It never mutates the stored judgment being replayed.
`sourceConfidenceSemantics`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.28.1Oct 29, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the agent knows this is not a pure read. The description adds a genuine interpretive caveat that annotations cannot convey: an unchanged result is explicit and must not be read as market safety or trading permission. It stops short of disclosing the write side effect (a new verdict may be persisted) or the write:portfolio requirement, both of which live only in the schema.

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?

Two sentences, front-loaded with the core verb and returned fields, with the caution placed last. The field enumeration is dense but each item earns its place by defining the delta payload; no filler or restated title.

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 an output schema present and 86% schema coverage, the description need not explain return structure, and it correctly focuses on the delta semantics and the unchanged-result caveat. The remaining gap is routing guidance against the many sibling verdict/decision tools.

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 86%, so the schema already documents limit, since, detail, refresh, symbols, and include_withheld thoroughly. The only parameter-adjacent statement in the description, 'Defaults to a fresh evaluation,' restates the refresh default already given in the schema, adding no new syntax or behavior detail.

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?

States a specific verb and resource ('Return only what changed for a persistent monitor-only watch') and enumerates exactly which fields constitute the delta: escalation label, risk band, direction, evidence coverage, threshold crossings, new evidence, and verdict IDs. This distinguishes it from adjacent siblings like fahali_get_verdict_history or fahali_get_portfolio_decision without needing to name them.

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 — poll an existing watch for changes — and the note that it 'Defaults to a fresh evaluation' clarifies the default mode. However, it never states when to choose this over siblings such as fahali_get_portfolio_decision (full verdict) or fahali_get_verdict_history, nor any exclusion or precondition.

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

Deploy Server