Skip to main content
Glama
Sign In

Georgia Commons

by org.georgiacommons
OverviewDiscussionsAdmin

Read one document

fetch
Read-onlyIdempotent

Read one document by id or any written form (bill:2025-2026/hb136, SB 3, opinion:S26A0060, 317 Ga. 528, code:16-11-127, O.C.G.A. § 16-11-127, ga-const:art-i-sec-i-para-iii, meeting:2026-02-05/house-rules, a page URL) as Markdown, at most max_chars (default 60,000) from start, with a pointer to the rest. metadata lists its versions, links grouped by relation, and parts (part reads one: a bill's votes or history, a meeting's transcript). A version id (...@key) reads that version. A hierarchy node (code:t16, code:t16/c11, ga-const:art-i) returns its children. A bill number used in more than one session returns the choices. around takes a passage citation from search and returns the text around it.

Input Schema

NameRequiredDescriptionDefault
idYesA document id or any written form of one (a bill number, docket, citation, page URL), a version id, or a hierarchy node.
partNodocument (default), or one of the parts metadata.parts lists.document
startNoCharacter offset to read from (the pointer at the end of a window gives it).
aroundNoA passage citation from search (version_id#start-end): the text around it.
includeNoParts to add to metadata (e.g. votes, history).
max_charsNoCharacters to return, 1,000 to 200,000.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / around
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "A passage citation from search (version_id#start-end): the text around it.",
+  "title": "Around"
+}
    • removedInput schema / properties / full
      Removed value: -{
-  "default": false,
-  "description": "Include the optional material the tool describes (for example votes and history, or the notes). Longer.",
-  "title": "Full",
-  "type": "boolean"
-}
    • changedInput schema / properties / id / description
      Previous value: -"A document id from search: code:44-7-34, ga-const:art-i-sec-i-para-i, us-const:amend-xiv, bill:2025-2026/hb136, opinion:S26A0060, or meeting:2026-02-05/house-rules."New value: +"A document id or any written form of one (a bill number, docket, citation, page URL), a version id, or a hierarchy node."
    • addedInput schema / properties / id / maxLength
      Added value: +300
    • addedInput schema / properties / include
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Parts to add to metadata (e.g. votes, history).",
+  "title": "Include"
+}
    • changedInput schema / properties / max_chars / description
      Previous value: -"Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part."New value: +"Characters to return, 1,000 to 200,000."
    • addedInput schema / properties / part
      Added value: +{
+  "default": "document",
+  "description": "document (default), or one of the parts metadata.parts lists.",
+  "title": "Part",
+  "type": "string"
+}
    • changedInput schema / properties / start / description
      Previous value: -"Where to start, as returned by the previous call's continuation pointer. 0 is the beginning."New value: +"Character offset to read from (the pointer at the end of a window gives it)."
  2. Changed6 schema fields changed
    • addedInput schema / properties / full / description
      Added value: +"Include the optional material the tool describes (for example votes and history, or the notes). Longer."
    • addedInput schema / properties / id / description
      Added value: +"A document id from search: code:44-7-34, ga-const:art-i-sec-i-para-i, us-const:amend-xiv, bill:2025-2026/hb136, opinion:S26A0060, or meeting:2026-02-05/house-rules."
    • addedInput schema / properties / id / minLength
      Added value: +1
    • addedInput schema / properties / max_chars
      Added value: +{
+  "default": 60000,
+  "description": "Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part.",
+  "maximum": 200000,
+  "minimum": 1000,
+  "title": "Max Chars",
+  "type": "integer"
+}
    • addedInput schema / properties / start
      Added value: +{
+  "default": 0,
+  "description": "Where to start, as returned by the previous call's continuation pointer. 0 is the beginning.",
+  "minimum": 0,
+  "title": "Start",
+  "type": "integer"
+}
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "id": {
-      "title": "Id",
-      "type": "string"
-    },
-    "metadata": {
-      "additionalProperties": true,
-      "title": "Metadata",
-      "type": "object"
-    },
-    "text": {
-      "title": "Text",
-      "type": "string"
-    },
-    "title": {
-      "title": "Title",
-      "type": "string"
-    },
-    "url": {
-      "title": "Url",
-      "type": "string"
-    }
-  },
-  "required": [
-    "id",
-    "title",
-    "text",
-    "url",
-    "metadata"
-  ],
-  "title": "FetchResult",
-  "type": "object"
-}New value: +null
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond them: default and maximum window sizes, truncation with a continuation pointer, ambiguity resolution (a bill number in multiple sessions returns choices), version-id reading via `...@key`, and hierarchy expansion. These are the exact runtime traits an agent cannot infer from structured fields.

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?

One dense paragraph, front-loaded with the primary operation before the mode variants, and no filler sentences. It is close to the upper limit of density — clauses like "A version id (`...@key`) reads that version" are terse to the point of requiring a second read.

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?

There is no output schema, so the description carries the return-value burden and does so: Markdown body, `max_chars` window, continuation pointer, and the metadata payload (versions, links by relation, parts). For a six-parameter read tool with four distinct modes, nothing an agent needs to invoke it correctly is absent.

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 100%, so baseline would be 3, but the description adds real meaning: concrete `part` values (a bill's votes or history, a meeting's transcript), the `start`/pointer relationship for paging, and the `around` argument's provenance from search citations. Only `include` is left mostly to the schema.

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?

Opens with a specific verb and resource ('Read one document') and immediately enumerates the id forms it accepts, which makes it trivially distinguishable from search, describe_site, and verify_quote. An agent knows exactly what this tool returns (Markdown) and on what object.

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?

Usage contexts are spelled out well: use `around` with a passage citation from search, use `metadata` to enumerate versions/links/parts, use `part` to pull a bill's votes or a meeting's transcript, and hierarchy nodes return children. What's missing is an explicit statement of when to prefer this over search or verify_quote, or an exclusion for oversized documents.

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

All Georgia Commons 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