VetAid — VA Claim Intelligence

Most-cited VA legal authorities

va_top_authorities

Read-onlyIdempotent

The legal authorities most frequently cited across the public Board of Veterans' Appeals corpus (1.9 million decisions, 1992 to present, updated nightly) — case law (e.g. Gilbert v. Derwinski for benefit-of-the-doubt, DeLuca, Correia, Sharp), 38 C.F.R. regulations, or 38 U.S.C. statutes — ranked by the number of DISTINCT decisions that cite them. Useful for explaining which precedents actually carry VA appeals. The response carries a 'basis' string saying exactly what was counted and over how many decisions; read it before quoting a number. Aggregate data only — no PII.

Args:
    kind: 'cases' (default), 'regulations', or 'statutes'.
    condition: optional condition keyword (e.g. 'ptsd', 'tinnitus', 'back')
        to rank authorities within that condition's decisions only.
    limit: how many to return, 1-100 (default 25).

Input Schema

TableJSON Schema

Name	Required	Default
`kind`	No	cases
`limit`	No
`condition`	No

Schema Changelog

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

First observedSep 6, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the readOnlyHint, idempotentHint, and destructiveHint annotations, the description adds meaningful behavioral context: the data is updated nightly, counts are based on DISTINCT decisions, and the response includes a 'basis' string that must be read before quoting a number. It also explicitly states there is no PII, which is a strong safety signal for an AI agent.

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 efficiently structured with a clear main clause followed by examples, counting methodology, usage guidance, and an Args block. Every sentence earns its place: corpus size, update cadence, distinct-decision ranking, basis-string caveat, and PII note all contribute actionable information. No filler or tautology.

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 the data source, counting method, parameter semantics, and safety profile, but with no output schema it could be slightly more explicit about the exact return structure (e.g., whether each authority includes its count). The mention of the 'basis' string is helpful, but a full sentence on the result items would make it complete.

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 has zero description coverage for all three parameters, so the description carries the full burden — and it does so excellently. It explains kind ('cases' default, 'regulations', or 'statutes'), condition with concrete examples ('ptsd', 'tinnitus', 'back') and its scoping effect, and limit with range and default. This fully compensates for the schema gap.

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 precise statement of what the tool does: it ranks the legal authorities most frequently cited across the Board of Veterans' Appeals corpus by distinct decision count. It names the resource (case law, C.F.R. regulations, statutes) and even gives examples (Gilbert v. Derwinski, DeLuca, Correia, Sharp). It is clearly distinguished from siblings like va_denial_stats and va_evidence_that_wins by focusing on 'top authorities' rather than outcomes or evidence.

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 provides clear context for when to use it: 'Useful for explaining which precedents actually carry VA appeals.' It does not explicitly name sibling alternatives or state when not to use it, but the use case is specific enough to guide an agent. It also clarifies the scope ('Aggregate data only — no PII'), reinforcing appropriate usage.

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

All VetAid — VA Claim Intelligence tools Inspect

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

A4.4/5.0

Disambiguation3/5

Most tools have clear individual roles, and the personal workflow tools are unambiguous. However, va_condition_intelligence overlaps with va_denial_stats, va_evidence_that_wins, and va_top_authorities, since it also reports outcome shares, evidence associations, and cited authorities, so selecting the right tool often depends on carefully reading the long descriptions.

Naming Consistency4/5

All names use lower_snake_case and are readable, with a consistent verb-first pattern for personal tools (get_my_*, list_my_*, run_my_*) and a va_ prefix for public data tools. The mix of verb-first and noun-phrase names is a minor inconsistency, but the two families are predictable and internally consistent.

Tool Count5/5

Nine tools is a well-scoped count for this domain. Each tool maps to a meaningful operation: four cover the personal case-analysis workflow and five cover aggregate VA data intelligence, with no obvious bloat at the tool-count level.

Completeness4/5

The surface covers the core lifecycle: list cases, check credits, run an analysis, retrieve the analysis summary, and query the main public intelligence areas (outcomes, evidence, authorities, and manual changes). Minor gaps exist, such as no explicit analysis-status endpoint for the 5-8 minute run and no separate condition-level denial-reason tool, but agents can work around these.

Resources

Need Help?