Skip to main content
Glama
LiLara-AI

ShadowGraph

Official

shadowgraph_confidence_evidence

Apply one piece of supporting or contradicting evidence to a decision's confidence. A stable key prevents double-counting; reuse restamps the decision, while new observations require new keys.

Instructions

Apply one keyed piece of supporting or contradicting evidence to a decision's confidence. Use shadowgraph_record_outcome once the decision has played out, shadowgraph_record_fact for an observation that can reopen it. Reusing key cannot double-count, but restamps the decision and commits a revision; a new observation needs a new key.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyYesREQUIRED stable dedupe key. Reuse the same key for the same observation so retries cannot double-count; use a NEW key for a genuinely new observation. There is no default, because a generated one would only be stable within a millisecond.
actorNoWho performed this write, such as an agent or person name. Stored for audit; never used to grant trust.
clientNoWhich client software performed this write, such as the host application name.
reasonYesWhy this evidence matters. Required, non-empty, and kept in the audit history.
supportsNoDefaults to true. false records contradicting evidence, moving confidence down instead of up.
sessionIdNoCaller-owned identifier that groups related writes in the audit trail.
decisionIdYesIdentifier of an existing decision, as returned by shadowgraph_record_decision, shadowgraph_search, or shadowgraph_retrieve.
observedAtNoISO 8601 time the evidence was observed. Defaults to now.
sourceClassNoClaimed origin, never proof: agent_claimed (the default), tool_observed, human_confirmed, or production_verified. It weights confidence only. An unrecognised label downgrades to agent_claimed, kept verbatim in sourceRaw.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesStable entity identifier.
goalNoWhat the decision was trying to achieve.
kindYesEntity kind: decision, attempt, memory, fact, relation, review, or alternative.
actorNoWho performed the write.
titleNoShort name of the decision.
chosenNoThe option that was chosen.
clientNoWhich client performed the write.
statusNoLifecycle state. Legacy records may carry a value this build does not recognise; shadowgraph_validate reports those.
outcomeNoThe recorded outcome, or null until one is recorded.
projectNoProject namespace; records imported from a schema that predates projects may carry null.
evidenceNoNormalised evidence entries: source, type, sourceClass, confidence, observedAt, detail.
createdAtNoISO 8601 creation time.
migrationNoPresent only on migrated records; records the legacy value a field was mapped from.
sessionIdNoSession identifier recorded with the write.
sourceRawNoThe original origin label when it differed from sourceClass. Audit only; never evidence.
updatedAtNoISO 8601 time of the last change.
confidenceNoAuditable confidence: initial, current (0-1), policy, a history entry per move, and a basis summarising the contributions it was folded from. Legacy records may lack basis.
supersedesNoIdentifiers of decisions this one replaced.
assumptionsNoAssumptions the decision rests on. Searchable content.
reviewAfterNoISO 8601 instant after which shadowgraph_maintain marks this decision stale.
sourceClassNoClaimed origin class recorded with the write. A claim, never proof.
alternativesNoRejected alternatives, each with id, label, reasonRejected, status, and the reopenWhen rules that make it reconsiderable.
supersededByNoIdentifier of the decision that replaced this one.
schemaVersionNoStorage schema version this entity was written under. A value above the build’s own version is preserved rather than downgraded.
failedAttemptsNoAttempt identifiers or notes attached to this decision.
Install Server

TDQS

A4.9/5.0
Behavior5/5

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

The description discloses side effects beyond the annotations: reusing a key 'cannot double-count, but restamps the decision and commits a revision.' This clarifies non-idempotent behavior and the write/commit nature of the call, complementing the readOnly=false and idempotentHint=false annotations.

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?

Three dense sentences with no filler. The core purpose is front-loaded, alternatives are named, and the critical key-reuse caveat is stated clearly.

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?

For a tool with 9 parameters, 100% schema coverage, and an output schema, the description provides the missing operational context: when to choose alternatives and what key reuse actually does. Nothing essential for selecting or invoking the tool is omitted.

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 the baseline is 3, but the description adds meaningful key semantics: reusing a key cannot double-count yet still restamps and commits a revision. This complements the schema's dedupe explanation, though it does not deeply elaborate other parameters.

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 opens with a specific verb and object: 'Apply one keyed piece of supporting or contradicting evidence to a decision's confidence.' It also names related siblings and clarifies this tool is for applying evidence, not for recording outcomes or facts.

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

Usage Guidelines5/5

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

It gives explicit routing guidance: use shadowgraph_record_outcome once the decision has played out, and shadowgraph_record_fact for an observation that can reopen it. It also explains the key-reuse caveat, telling agents when a new key is required.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LiLara-AI/shadowgraph'

If you have feedback or need assistance with the MCP directory API, please join our Discord server