VetAid — VA Claim Intelligence

BVA outcomes by condition

va_condition_intelligence

Read-onlyIdempotent

Real Board of Veterans' Appeals outcome data for one VA condition, from 1.9 million public BVA decisions, 1992 to present, updated nightly: the share of decided issues GRANTED / DENIED / REMANDED / DISMISSED (shares of all decided issues, so they sum to 100%; complete years, with an all-years block labelled separately), the year-by-year trend, which kinds of evidence went with a grant versus without, the denial reasons tagged in a smaller hand-tagged sample (labelled with its own n), and the legal authorities most cited. Aggregate data only — no PII, and a base rate for appealed cases, not a prediction for one veteran.

Args:
    condition: VA condition keyword, e.g. 'ptsd', 'tinnitus', 'sleep apnea',
        'back', 'knee', 'depression', 'gerd', 'migraines'. An unmatched
        value returns the list of valid condition keys.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`condition`	Yes

Schema Changelog

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

First observedSep 6, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so no contradiction exists. The description goes well beyond annotations by disclosing the underlying dataset size, time range, nightly updates, output composition, aggregate/no-PII nature, the base-rate framing, and the unusual behavior of returning valid condition keys for an unmatched input.

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?

The opening sentence is dense and overloaded with parenthetical caveats, but every clause contributes real decision-useful information rather than filler. The Args section is clearly separated and the content is front-loaded with the core purpose. A lighter restructure would help, but the density is justified by the tool's broad output.

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, the description must explain what the invocation returns, and it does: outcome shares, trends, evidence associations, denial reasons, authorities, and the separate handling of all-years and hand-tagged samples. It also documents input behavior, data provenance, and the key limitation that this is not a prediction. Nothing essential is missing for correct selection and invocation.

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 schema provides no description for the single condition parameter, so the description carries full responsibility. It supplies concrete example values, clarifies that these are VA condition keywords, and explicitly documents the unmatched-value behavior. This fully compensates for the 0% schema description coverage.

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 clearly identifies the tool as providing BVA outcome data for one VA condition and enumerates the specific result components: grant/deny/remand/dismiss shares, trends, evidence associations, denial reasons, and cited authorities. It does not explicitly differentiate itself from sibling tools like va_denial_stats or va_evidence_that_wins, which keeps it from 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?

The description gives clear context about when this fits: when an agent needs population-level BVA outcomes for a single condition, framed as aggregate base rates rather than a prediction for an individual veteran. However, it does not state explicit alternatives or exclusions, such as when to prefer va_denial_stats or va_evidence_that_wins, so guidance is contextual but incomplete.

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?