bva-corpus

Search BVA decisions

search_bva_decisions

Read-onlyIdempotent

Search the incomplete historical Board of Veterans’ Appeals archive using English full-text websearch over summaries, reasoning and condition text, with exact condition and optional disposition, exposure, theory, PACT Act and date filters. Full-text matching is not literal substring matching. Returns up to 25 recent matching decisions, not a total count. New imports are paused; archive ends April 30, 2026. Summaries are AI-assisted; verify each issue against the original VA source.

Input Schema

Name	Required	Description
`limit`	No
`query`	No	English full-text websearch over summaries, reasoning and condition text, as in the public decision library. Not literal substring matching.
`date_to`	No
`condition`	No	A claimed condition, e.g. "tinnitus", "PTSD".
`date_from`	No
`disposition`	No
`is_pact_act`	No
`exposure_basis`	No
`service_connection_theory`	No

Output Schema

Name	Required	Description
`data`	Yes	Tool-specific result payload.
`link`	Yes	Tagged deep link into the matching veterans-rights.com page.
`disclaimer`	Yes	Standing not-legal-advice / not-VA framing.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 10, 2026

changedInput schema / properties / query / description

Previous value: -"Free-text search over the plain-English decision summary."New value: +"English full-text websearch over summaries, reasoning and condition text, as in the public decision library. Not literal substring matching."

Changed1 schema field changedJul 15, 2026
- changedInput schema / required
```
Previous value: -[
-  "limit"
-]New value: +[]
```

Changed1 schema field changedJun 18, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "data": {
+      "description": "Tool-specific result payload.",
+      "type": "object"
+    },
+    "disclaimer": {
+      "description": "Standing not-legal-advice / not-VA framing.",
+      "type": "string"
+    },
+    "link": {
+      "description": "Tagged deep link into the matching veterans-rights.com page.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "data",
+    "link",
+    "disclaimer"
+  ],
+  "type": "object"
+}

First observedJun 13, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond the readOnly/idempotent/openWorld annotations: discloses that matching is not literal substring, that up to 25 recent results are returned rather than a total count, that the archive ends April 30 2026 with imports paused, and that summaries are AI-assisted and should be verified against the original VA source. These are material behavioral facts an agent needs to interpret results.

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?

Four sentences, front-loaded with the search scope before the caveats. Each sentence earns its place — query semantics, result cap, archive cutoff, and verification warning are all actionable. Slightly dense but not padded.

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?

For a 9-parameter read-only search with an output schema, the description covers the archive's limits, result semantics, and data-quality caveats well. Enum parameters are self-describing in the schema. The main omission is no explicit routing guidance against sibling tools like find_similar_appeals.

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 description coverage is only 22% across 9 params, so the description must compensate. It clarifies query semantics (websearch, not substring; already in schema but reinforced), defines condition as an exact match, and enumerates the optional filter dimensions (disposition, exposure, theory, PACT Act, dates). limit is only indirectly covered by the 'up to 25' statement, leaving a small 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?

States a specific verb (Search) and resource (incomplete historical BVA archive), plus the search mode (English full-text over summaries, reasoning, condition text). An agent can immediately tell this is a decision-text search tool rather than a condition lookup or appeals-explainer tool. Sibling overlaps with find_similar_appeals are not explicitly addressed, but the resource scope is unambiguous.

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 implies usage through its filter list (exact condition, disposition, exposure, theory, PACT Act, dates) and notes the archive is incomplete and imports are paused, but it never states when to prefer this over find_similar_appeals or other siblings, nor any exclusions. Usage is inferable rather than explicit.

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

All bva-corpus tools Inspect

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

Need Help?