Skip to main content
Glama
Sign In

Global law

by com.lexifina
OverviewDiscussionsAdmin

Resolve citations

resolve_citations
Read-onlyIdempotent

Read every citation in a piece of text (a brief, a judgment, an email) and resolve each to its provision, with its state on a date: in force or not, the law that last changed it, and the next change.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "resolve_citations"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoAn in-force date, YYYY-MM-DD, or "today". Defaults to today.
textYesUp to 50000 characters.
max_resultsNoAt most this many distinct provisions are looked up (default 50, at most 100).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / max_results / description
      Previous value: -"At most this many distinct provisions are looked up (default 50, most 100)."New value: +"At most this many distinct provisions are looked up (default 50, at most 100)."
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

The annotations already establish readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds the useful 'every citation' bulk-processing scope and the per-citation state-on-a-date output, but it is silent on what happens to citations that cannot be resolved, on truncation when a text exceeds the max_results cap, and on cost/latency for 50k-character inputs. That leaves meaningful behavioral gaps for a batch 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?

A single front-loaded sentence carries the action, the input domain, and the full result shape with no filler or redundancy. The colon-list structure makes the output fields scannable rather than buried in prose.

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 100% parameter coverage, the description only needs to frame the operation, which it does well. It is slightly thin on failure modes—unresolvable or ambiguous citations, and behavior when the text exceeds 50k characters or the max_results cap—which an agent would want before invoking on a long document.

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 coverage is 100%, so all three parameters are already documented in the input schema, making 3 the baseline. The description does motivate the 'date' parameter by framing resolution as 'with its state on a date', but it adds no format, defaulting, or edge-case detail (e.g., historical dates before a provision existed) beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Read every citation in a piece of text ... and resolve each to its provision') and even enumerates the resolved payload: in-force status, the law that last changed it, and the next change. It clearly separates this from lookup-style siblings such as find_provision by operating over an arbitrary text's citations, but it never names or contrasts an alternative explicitly, so it stops short of a 5.

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 only implied through input examples ('a brief, a judgment, an email'), which conveys the intended context without stating conditions or exclusions. There is no guidance on when to prefer find_provision or check_precedent instead, nor on what to do with partial or ambiguous matches. Adequate but the agent must infer the routing.

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

All Global law toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources