Skip to main content
Glama
Sign In

GovGazette

by io.github.mooshee
OverviewDiscussionsAdmin

Search exclusions

search_exclusions
Read-onlyIdempotent

Filter active exclusion records by agency, program, classification, geography and dates. Limit is a maximum; large records can produce a smaller page with page_size_limited true. Continue with next_cursor and unchanged filters and limit. Preserve generation and read coverage.freshness for source age and warnings; results are dated evidence, not clearance.

Input Schema

NameRequiredDescriptionDefault
qNoName, identifier, or other text to find in active exclusion records.
limitNoMaximum records to return, from 1 to 50. Large records may produce a smaller page; continue with next_cursor and unchanged filters and limit.
stateNoUS state name or postal code in the exclusion record.
agencyNoExcluding agency name or code.
cursorNoOpaque next_cursor from a previous search response.
countryNoCountry name or code in the exclusion record.
programNoExclusion program name or code.
generationNoRetained snapshot UUID; omit for the current snapshot.
effective_toNoInclude records effective on or before this ISO date.
classificationNoOfficial SAM exclusion classification code or label.
effective_fromNoInclude records effective on or after this ISO date.

Output Schema

NameRequiredDescriptionDefault
itemsYes
coverageYesDated source coverage, or an unavailable status.
generationYes
next_cursorNo
page_size_limitedYesWhole records were deferred to next_cursor to fit the response budget. Continue with the same filters and requested limit.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum records to return, up to the service page limit."New value: +"Maximum records to return, from 1 to 50. Large records may produce a smaller page; continue with next_cursor and unchanged filters and limit."
    • addedOutput schema / properties / page_size_limited
      Added value: +{
+  "description": "Whole records were deferred to next_cursor to fit the response budget. Continue with the same filters and requested limit.",
+  "type": "boolean"
+}
    • changedOutput schema / required
      Previous value: -[
-  "generation",
-  "items",
-  "coverage"
-]New value: +[
+  "generation",
+  "items",
+  "page_size_limited",
+  "coverage"
+]
  2. Changed3 schema fields changed
    • addedOutput schema / $defs / SourceFreshness / properties / attention_required
      Added value: +{
+  "type": "boolean"
+}
    • addedOutput schema / $defs / SourceFreshness / properties / warn_age_seconds
      Added value: +{
+  "description": "Early-warning boundary, separate from the stale-source boundary.",
+  "format": "int64",
+  "type": "integer"
+}
    • changedOutput schema / $defs / SourceFreshness / required
      Previous value: -[
-  "state",
-  "evaluated_at",
-  "max_age_seconds"
-]New value: +[
+  "state",
+  "evaluated_at",
+  "max_age_seconds",
+  "warn_age_seconds",
+  "attention_required"
+]
  3. Changed4 schema fields changed
    • addedOutput schema / $defs / ExclusionCoverage
      Added value: +{
+  "properties": {
+    "freshness": {
+      "$ref": "#/$defs/SourceFreshness",
+      "description": "Fresh, stale, unknown or unavailable, with age and the 24-hour warning policy."
+    },
+    "observed_at": {
+      "description": "Observation time does not replace the official source timestamp.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "scope": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "sha256": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "source_date": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "source_url": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "status": {
+      "description": "Present as unavailable when no SAM coverage exists in this generation.",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "freshness"
+  ],
+  "type": "object"
+}
    • addedOutput schema / $defs / FreshnessState
      Added value: +{
+  "enum": [
+    "fresh",
+    "stale",
+    "unknown",
+    "unavailable"
+  ],
+  "type": "string"
+}
    • addedOutput schema / $defs / SourceFreshness
      Added value: +{
+  "properties": {
+    "evaluated_at": {
+      "description": "UTC time when age was evaluated; source and observation dates are unchanged.",
+      "type": "string"
+    },
+    "max_age_seconds": {
+      "description": "Explicit warning threshold for this daily snapshot. Not a scheduler promise.",
+      "format": "int64",
+      "type": "integer"
+    },
+    "source_age_seconds": {
+      "description": "Age of the official source timestamp, never the import or enrichment timestamp.",
+      "format": "int64",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "state": {
+      "$ref": "#/$defs/FreshnessState"
+    },
+    "warning": {
+      "description": "User-facing warning, or null when within the warning threshold.",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "state",
+    "evaluated_at",
+    "max_age_seconds"
+  ],
+  "type": "object"
+}
    • changedOutput schema / properties / coverage / $ref
      Previous value: -"#/$defs/JsonObject"New value: +"#/$defs/ExclusionCoverage"
  4. Changed2 schema fields changed
    • addedInput schema / properties / limit / maximum
      Added value: +50
    • changedInput schema / properties / limit / minimum
      Previous value: -0New value: +1
  5. Changed12 schema fields changed
    • addedInput schema / properties / agency / description
      Added value: +"Excluding agency name or code."
    • addedInput schema / properties / classification / description
      Added value: +"Official SAM exclusion classification code or label."
    • addedInput schema / properties / country / description
      Added value: +"Country name or code in the exclusion record."
    • addedInput schema / properties / cursor / description
      Added value: +"Opaque next_cursor from a previous search response."
    • addedInput schema / properties / effective_from / description
      Added value: +"Include records effective on or after this ISO date."
    • addedInput schema / properties / effective_to / description
      Added value: +"Include records effective on or before this ISO date."
    • addedInput schema / properties / generation / description
      Added value: +"Retained snapshot UUID; omit for the current snapshot."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum records to return, up to the service page limit."
    • addedInput schema / properties / program / description
      Added value: +"Exclusion program name or code."
    • addedInput schema / properties / q / description
      Added value: +"Name, identifier, or other text to find in active exclusion records."
    • addedInput schema / properties / state / description
      Added value: +"US state name or postal code in the exclusion record."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$defs": {
+    "JsonObject": {
+      "description": "Source-specific JSON map. The envelope is stable; map keys vary by official source.",
+      "type": "object"
+    },
+    "RecordSummary": {
+      "properties": {
+        "data": {
+          "$ref": "#/$defs/JsonObject",
+          "description": "Source-specific fields, including provenance and official identifiers."
+        },
+        "id": {
+          "description": "Stable identifier for a record in this generation.",
+          "type": "string"
+        },
+        "summary": {
+          "description": "Short searchable text, when returned by this operation.",
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "title": {
+          "description": "Human-readable record title.",
+          "type": "string"
+        },
+        "url": {
+          "description": "Public canonical path for the record.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "id",
+        "title",
+        "url",
+        "data"
+      ],
+      "type": "object"
+    }
+  },
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "properties": {
+    "coverage": {
+      "$ref": "#/$defs/JsonObject",
+      "description": "Dated source coverage, or an unavailable status."
+    },
+    "generation": {
+      "type": "string"
+    },
+    "items": {
+      "items": {
+        "$ref": "#/$defs/RecordSummary"
+      },
+      "type": "array"
+    },
+    "next_cursor": {
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "generation",
+    "items",
+    "coverage"
+  ],
+  "type": "object"
+}
  6. Added
  7. Removed
  8. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world). The description adds genuinely useful behavior beyond that: pages may come back smaller than limit with page_size_limited true, cursor must be paired with unchanged filters, and the data is 'dated evidence, not clearance' — a meaningful validity caveat. It stops short of describing freshness staleness thresholds.

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?

Front-loaded with the purpose sentence, then pagination mechanics, then the freshness/validity caveat. Slightly dense with internal jargon (page_size_limited, coverage.freshness, generation) and mildly redundant with the limit and cursor schema descriptions, but no filler sentences.

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 explained, and the description covers pagination, cursor discipline, snapshot/generation retention, and a warning about data recency. The only real gap is disambiguation from the many sibling search/check tools.

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 description coverage is 100%, so every one of the 11 parameters is already documented, making 3 the baseline. The description restates the filter facet categories but adds no syntax, accepted values, or matching semantics beyond the schema, so it neither compensates nor improves.

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 a specific verb and resource — 'Filter active exclusion records' — and enumerates the filterable facets (agency, program, classification, geography, dates). It does not, however, distinguish itself from the close sibling check_exclusions, which likely returns a single match versus this list/filter behavior, so an agent must infer the boundary.

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?

Provides clear operational guidance for the paginated loop ('Continue with next_cursor and unchanged filters and limit'), which implies this is a multi-page list tool. But it never says when to choose it over check_exclusions, search, exclusion_changes, or exclusion_context, leaving the sibling-selection decision to inference.

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

All GovGazette 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