Skip to main content
Glama
LiLara-AI

ShadowGraph

Official

shadowgraph_context

Build a project's working set of decisions, assumptions, and failures before a task. Evaluate reopen rules, persist signals, and commit a revision for current context.

Instructions

Build one project's working set before a consequential task: decisions, stale assumptions, failed attempts, open reviews. shadowgraph_search or shadowgraph_retrieve look one thing up, shadowgraph_recall reads scoped memory, shadowgraph_review only evaluates. Not a read: it evaluates reopen rules, can persist signals, and commits a revision.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
factsNoFact key/value overrides evaluated instead of the stored facts of the same key. Stored facts are used for every key not listed here, so reopen rules still work after a restart.
limitNoMaximum items per collection, 1-1000, applied to each collection independently. Omit for the default of 50.
projectNoProject namespace. Defaults to "default"; an empty string is rejected.
changedFactsNoFact keys that just changed. Only string-form reopenWhen rules match this list; it is an ephemeral signal, not durable state.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectYesThe project this context describes.
openReviewsYesDecisions currently due for reconsideration.
completenessYesPer-collection completeness. context returns five named collections, so one page object cannot describe it.
activeDecisionsYesDecisions in a current, actionable state: proposed, planned, in_progress, executed, validated, or reconsidered.
staleAssumptionsYesFacts that are no longer active, such as superseded or expired ones, which earlier decisions may still rest on.
suggestedQuestionsYesQuestions for the low-confidence decisions in this project.
failedAttemptsToAvoidYesAttempts whose result mentions failure, regression, or error.
Install Server

TDQS

A4.4/5.0
Behavior4/5

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

With all annotations false, the description carries the burden of disclosure and largely meets it: 'Not a read: it evaluates reopen rules, can persist signals, and commits a revision' clearly communicates mutation and side effects. It could go further by specifying what a committed revision entails, but it is honest and materially informative.

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 sentences, each earning its place: purpose, sibling differentiation, and the critical non-read caveat. The structure front-loads the primary intent before alternatives and caveats.

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?

The description covers purpose, usage boundary, side effects, and sibling routing, and an output schema exists to handle return values. Minor gaps remain around what exactly a 'revision' is and how reopen rules behave, but these do not block correct invocation.

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 100% and every parameter already has a detailed description. The narrative description adds no parameter-specific semantic value, so the baseline 3 is appropriate.

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 resource: 'Build one project's working set' and lists what that set contains. It then explicitly differentiates itself from shadowgraph_search, shadowgraph_retrieve, shadowgraph_recall, and shadowgraph_review, making sibling confusion unlikely.

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 states when to use this tool ('before a consequential task') and names concrete alternatives for single lookups, scoped memory reads, and evaluations. It also adds the crucial exclusion 'Not a read,' preventing misuse for read-only needs.

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