Skip to main content
Glama

Lexiara

by org.lexiara

What is waiting for a human verdict

list_review_queue
Read-onlyIdempotent

The AUTO-GATED backlog from one place, newest first: unreviewed article-level transposition links with BOTH provision texts side by side and the stored reasoning, model/low-confidence concept tags, draft topic descriptions and jurisdiction notes, and recorded findings (gaps and divergences a round could not decide). Filter by kind, vertical and jurisdiction. EVERYTHING HERE IS UNREVIEWED EVIDENCE — cite none of it as a finding. This tool is READ-ONLY: verdicts are set only by a human with a 'reviewer' key, and no MCP tool can set one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNoComma-separated kinds: transposition, tag, topic-description, jurisdiction-note, finding. Omit for all.
charsNoCharacters of provision text per side. Omit for the WHOLE text, which is the default: a character budget once hid two parts of a French code article and produced two false absences.
limitNoMaximum items, default 20, max 100.
offsetNoSkip this many items — the queue is paged, not sampled.
verticalNoVertical id, e.g. 'eu-consumer', 'fr-consumer', 'es-consumer'.
jurisdictionNoISO country filter, e.g. 'UK', 'FR', 'EU'.
lowConfidenceNoAlso list non-model classifier tags at or below this confidence. Omit for model tags only — the keyword baseline's weak tail is 24 000 rows and would bury the 157 links a verdict changes.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, and non-destructive hints, and the description adds meaningful behavioral context beyond them: verdicts can only be set by a human with a 'reviewer' key, no MCP tool can set one, and everything returned is unreviewed evidence. This is precisely the kind of extra context an agent needs and no annotation provides.

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?

The description is dense but every sentence earns its place: the first front-loads the resource and ordering, the second covers filters, and the final two carry critical usage warnings about unreviewed evidence and read-only behavior. There is no filler or redundant restatement of the tool name.

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?

With no output schema present, the description carries the burden of explaining what the tool returns, and it does: item kinds, side-by-side provision texts, stored reasoning, ordering, filters, and key caveats. An agent has enough information to call this tool correctly and interpret its results responsibly.

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 the schema itself already provides rich parameter detail, including the chars truncation warning and the lowConfidence tail-size warning. The description only repeats filter dimensions ('kind, vertical and jurisdiction') and adds no new parameter-level semantics, so the baseline of 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 names a specific resource — the 'AUTO-GATED backlog' of unreviewed items — and enumerates exactly what it returns: transposition links with both provision texts, reasoning, low-confidence tags, draft topic descriptions, jurisdiction notes, and recorded findings. It also states the ordering ('newest first'), making it unmistakable from sibling research/list tools.

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?

The description gives clear context for when to use the tool: when human verdicts are pending and you need the unreviewed backlog, with explicit filters by kind, vertical, and jurisdiction. It includes a strong exclusion — 'cite none of it as a finding' — but it does not name alternative tools or conditions for when-not to use it.

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

All Lexiara toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, and descriptions carefully separate overlapping areas such as definition lookup, cross-references, and transposition links. A few citation/graph tools (related_works, work_mentions, find_national_implementations, provision_context) could be confused at a glance, but their granularity and direction are explicitly differentiated.

Naming Consistency3/5

Naming follows a readable all-lowercase-snake_case style, but conventions are mixed: roughly half are imperative verb_object names (lookup_provision, search_legislation, list_topics) while the rest are bare noun-phrase view names (provision_context, recent_changes, work_mentions). The pattern is understandable but not uniform.

Tool Count4/5

At 18 tools, the set is slightly above the ideal 3-15 range, but each tool maps to a distinct research query or data product. The count is justified by the breadth of legal-research operations rather than redundancy.

Completeness5/5

The surface covers the domain thoroughly: search, provision lookup, definitions, multilingual terms, cross-references, amendment history, transposition links, topics, coverage, updates, and review workflows. The explicit read-only design means absent write operations are a deliberate boundary, not a gap.

Resources