Skip to main content
Glama

Search legal vectors

search_legal_vectors
Read-only

Free bounded hybrid retrieval of affirmatively cleared current state-law provisions. Partial coverage only; no persons, companies, courts or other corpora. Returns the canonical page with RT attribution, clocks and ten-minute-or-midnight expiry. Continue with the same query/result_set and next_offset; restart_required needs an explicit new search. Unavailable and rate_limited are errors, never empty results. No snapshot or generation/RAG call. Use browse_catalog(kind=legal_search) for the separate literal snapshot search. Do not look up natural persons.

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": {
      "query": "<query>"
    },
    "name": "search_legal_vectors"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYesLegal query, at most 512 UTF-8 bytes and 256 encoder tokens
offsetNo
result_setNoOpaque fixed-result token; reuse with the same query and next_offset

Output Schema

NameRequiredDescriptionDefault
hitsYes
modeYes
limitYes
stateYes
noticeYes
offsetYes
sourcesYes
coverageYes
has_moreYes
returnedYes
checked_atYes
exclusionsYes
expires_atYes
generationYes
result_setYes
next_offsetYes
release_shaYes
validity_dateYes
clock_meaningsYes
policy_versionYes
search_limitedYes
ranking_versionYes
clearance_digestYes
contract_versionYes
generation_built_atYes
page_limited_by_bytesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description goes well beyond them: partial coverage, ten-minute-or-midnight expiry, error semantics ('unavailable and rate_limited are errors, never empty results'), and result-set invalidation producing restart_required. The gaps are only that 'RT attribution' and the clocks are not explained, so an agent knows the traits exist but not quite what they mean.

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?

Scope and coverage limits are front-loaded before operational detail, and every sentence carries a distinct constraint (coverage, return shape, pagination, error taxonomy, sibling routing, exclusion) with no restatement of the name or title.

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?

An output schema exists so return values need not be enumerated, yet the description still sketches the canonical page, attribution and expiry clocks. Combined with error taxonomy and continuation rules, an agent has what it needs to call and page correctly; only the undefined 'RT attribution' and the offset/next_offset relationship leave light ambiguity.

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 50% (query and result_set documented, limit and offset bare), and the description compensates by giving result_set its real semantics: an opaque fixed-result token that must be reused with the same query and the next_offset. That is meaningful added meaning beyond the schema, but the naming mismatch ('next_offset' versus the schema's 'offset') and the untouched limit/offset parameters keep it below the top.

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?

States the resource precisely ('affirmatively cleared current state-law provisions') and bounds it negatively ('no persons, companies, courts or other corpora'), so an agent knows exactly what corpus is searched. The verb phrasing 'Free bounded hybrid retrieval' is jargon-heavy and never plainly says 'search', but the sibling exclusion of browse_catalog(kind=legal_search) removes ambiguity about which tool does what.

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?

Explicitly names the alternative ('Use browse_catalog(kind=legal_search) for the separate literal snapshot search') with the condition that selects it, and adds a hard exclusion ('Do not look up natural persons'). It also spells out continuation behavior (same query/result_set with next_offset) and the restart_required escape hatch, leaving no inference to the agent.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources