Skip to main content
Glama

Experimental Legal Grounding

Server Details

Experimental GDPR grounding: rules, preconditions, exceptions, exact quotes, and citation checks.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.5/5 across 3 of 3 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool has a distinct and clearly defined purpose: get_catalog provides the vocabulary, retrieve_evidence fetches evidence packets, and validate_checks citations. No two tools overlap in functionality.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (get_catalog, retrieve_evidence, validate_claims), making their actions predictable and easy to interpret.

Tool Count4/5

With only three tools, the server is tightly scoped to the legal grounding workflow. While it is a minimal set, it covers the essential steps without excess, though a few more might be expected for completeness.

Completeness4/5

The tools cover the core workflow: catalog exploration, evidence retrieval, and claim validation. However, there is no tool for querying or generating an answer directly, which might require the agent to compose multiple calls. Minor gaps exist but do not severely hinder the primary purpose.

Available Tools

3 tools
get_catalogAInspect

Vocabulary map of the corpus: obligation clusters (with support status), regulation terms, everyday-phrase bridges, and corpus boundaries (topics governed by law OUTSIDE this corpus, e.g. cookie consent under ePrivacy). Call this first to translate a user's question into cluster/term selectors, and to learn where honest answers require referral rather than assertion.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
Behavior4/5

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

Without annotations, the description discloses the tool's return content in detail (clusters, terms, bridges, boundaries) and even notes what is outside the corpus. This is sufficient for a read-only catalog tool.

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 concise (3 sentences) and front-loaded with the core purpose. Every sentence adds value: content description, usage guidance, and boundary explanation.

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?

Given zero parameters and the presence of an output schema, the description fully covers what the tool does and how to use it. It explains the catalog's contents and its role as a first step, making it complete.

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?

No parameters exist, so schema coverage is trivially 100%. The description adds meaning about what the output contains, which is valuable. Baseline 4 applies per rules.

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 clearly defines the tool as a 'vocabulary map of the corpus' and lists specific elements (obligation clusters, regulation terms, etc.), distinguishing it from sibling tools that retrieve evidence or validate claims.

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 explicitly says 'Call this first to translate a user's question into cluster/term selectors', providing clear guidance on when to use it. It also mentions learning where referral is needed, adding context, though it does not explicitly state when not to use.

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

retrieve_evidenceAInspect

Evidence packets for legal topics. Selectors (union): cluster ids and/or term keys from get_catalog, and/or free_text (deterministic lexical+bridge matching only — no semantic search). Each packet returns primary rules PLUS their preconditions and exceptions with byte-exact quotes and stable rule ids; mandatory packet content is never truncated. Use every part: presenting a duty without its packet's exceptions or preconditions will fail validate_claims. corpus_coverage tells you when the governing law is outside the corpus — qualify or refer, don't guess.

ParametersJSON Schema
NameRequiredDescriptionDefault
roleNo
termsNo
clustersNo
free_textNo
max_supplemental_rules_per_packetNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
Behavior4/5

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

Discloses key behaviors: deterministic lexical+bridge matching (no semantic search), byte-exact quotes, stable rule ids, mandatory packet content never truncated, and corpus_coverage field. No annotations provided, so description carries burden well.

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?

Packed with information in a few sentences, front-loading the purpose. Dense but efficient, no unnecessary words.

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?

Given the output schema exists, description sufficiently covers packet content and selector behavior. References sibling tools and provides context for result interpretation, making it mostly complete for a complex tool.

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?

Explains clusters, terms (from get_catalog), and free_text selectors, but does not describe 'role' or 'max_supplemental_rules_per_packet'. With 0% schema coverage, description partially compensates for three of five 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 clearly states 'Evidence packets for legal topics' and specifies the selectors: cluster ids, term keys from get_catalog, and free_text. It distinguishes from siblings by referencing get_catalog and validate_claims directly.

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?

Provides practical usage advice: 'Use every part' and warns that omitting exceptions or preconditions will fail validate_claims. Also explains corpus_coverage and the deterministic nature of free_text matching.

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

validate_claimsAInspect

Verify a drafted answer's legal citations before presenting it. Each claim: {claim_id, assertion, cluster_id (optional, enables on-point checks), citations: [{rule_id, quote}]}. Verdicts (first match wins): unknown_reference (fabricated id), misquoted (canonical quote returned — fix and re-validate), wrong_provision (citation off-topic for the cluster), outside_corpus (abstain/refer to the named external law), qualified_by_exception / qualified_by_precondition (add the returned exception/precondition citations and re-validate, or qualify your prose), supported, unsupported. IMPORTANT: 'supported' certifies citation-grounding only (semantic_validation_performed is always false) — it never certifies that your legal conclusion is correct.

ParametersJSON Schema
NameRequiredDescriptionDefault
claimsYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
Behavior5/5

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

With no annotations provided, the description fully discloses behavior: the 'first match wins' ordering, the definitive meanings of each verdict, and the explicit caveat that 'supported' does not certify legal conclusion correctness and that 'semantic_validation_performed' is always false. No behavioral aspect is hidden.

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 a single focused paragraph that begins with the core purpose, then immediately provides the input format, then lists verdicts in a compact inline format, and closes with a critical note. Every sentence is necessary and informative with no repetition or filler.

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?

Given the tool's complexity (one parameter with nested structure, many verdicts), the description covers input structure, all verdicts and their implications, and an important behavioral limitation. Output schema exists and is not required in the description. The description is complete for an agent to correctly invoke and interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides only a minimal definition ('array of objects with additionalProperties: true'), so schema coverage is 0%. The description compensates fully by specifying the exact structure of each claim: claim_id, assertion, optional cluster_id, and citations array with rule_id and quote. It also explains the verdicts, which are essential for correct usage.

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 starts with a clear verb+resource: 'Verify a drafted answer's legal citations before presenting it.' It details the input structure and all possible verdicts, making the tool's purpose unmistakable. It is easily distinguished from sibling tools get_catalog and retrieve_evidence, which are data retrieval 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 states when to use the tool ('before presenting'), and outlines required actions for each verdict (e.g., 'fix and re-validate', 'qualify your prose'). It also clarifies the limitation that 'supported' only certifies citation-grounding, not correctness. However, it does not explicitly contrast with sibling tools or provide when-not-to-use scenarios.

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

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.

Resources