Agent Reliability

Sources behind Agent Reliability

get_sources

Read-onlyIdempotent

The instance's source registry — each entry with its evidence tier, reliability and access date. PAGED: 25 entries by default, 200 at most, and a response budget of about 64 KB per call — a page over budget comes back shorter WITH a next_cursor, never truncated. Read next_cursor and call again to continue; its absence means you have the last page. Filter by object_id, tier, host or accessed_since to avoid paging through a registry you do not need. Use this when you need the registry entry behind a citation, or a sample of the whole registry to judge the corpus before trusting it; get_entity already tells you which sources a claim cites.

Input Schema

TableJSON Schema

Name	Required	Description
`host`	No	Only sources whose URL is served by this host, compared without a leading www. A source with no URL never matches.
`tier`	No	Only sources of this evidence tier, spelled exactly as get_sources reports it.
`limit`	No	How many entries to return. Defaults to 25.
`cursor`	No	Continue from a previous call: pass the next_cursor it returned. Opaque; do not construct one.
`object_id`	No	Restrict the answer to the sources cited by this knowledge object. Omit it to page the whole registry.
`accessed_since`	No	Only sources accessed on or after this ISO date (YYYY-MM-DD).

Output Schema

TableJSON Schema

Name	Required	Description
`found`	Yes
`total`	Yes	How many sources matched the filters, before paging.
`sources`	Yes
`recovery`	No
`returned`	Yes
`next_cursor`	No	Pass to the next call to continue. ABSENT means this was the last page.

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedSep 6, 2026

addedInput schema / properties / accessed_since

Added value: +{
+  "description": "Only sources accessed on or after this ISO date (YYYY-MM-DD).",
+  "maxLength": 10,
+  "minLength": 4,
+  "type": "string"
+}

addedInput schema / properties / cursor

Added value: +{
+  "description": "Continue from a previous call: pass the next_cursor it returned. Opaque; do not construct one.",
+  "maxLength": 200,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / host

Added value: +{
+  "description": "Only sources whose URL is served by this host, compared without a leading www. A source with no URL never matches.",
+  "maxLength": 120,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / limit

Added value: +{
+  "description": "How many entries to return. Defaults to 25.",
+  "maximum": 200,
+  "minimum": 1,
+  "type": "integer"
+}

changedInput schema / properties / object_id / description

Previous value: -"Restrict the answer to the sources cited by this knowledge object. Omit it to get the instance's whole source registry."New value: +"Restrict the answer to the sources cited by this knowledge object. Omit it to page the whole registry."

addedInput schema / properties / tier

Added value: +{
+  "description": "Only sources of this evidence tier, spelled exactly as get_sources reports it.",
+  "maxLength": 60,
+  "minLength": 1,
+  "type": "string"
+}

addedOutput schema / properties / next_cursor

Added value: +{
+  "description": "Pass to the next call to continue. ABSENT means this was the last page.",
+  "type": "string"
+}

addedOutput schema / properties / returned

Added value: +{
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}

addedOutput schema / properties / total

Added value: +{
+  "description": "How many sources matched the filters, before paging.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}

changedOutput schema / required

Previous value: -[
-  "found",
-  "sources"
-]New value: +[
+  "found",
+  "sources",
+  "total",
+  "returned"
+]

Changed1 schema field changedSep 1, 2026

addedInput schema / properties / object_id / description

Added value: +"Restrict the answer to the sources cited by this knowledge object. Omit it to get the instance's whole source registry."

Changed1 schema field changedAug 26, 2026

addedOutput schema / properties / recovery

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "available": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "available_count": {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "available_truncated": {
+      "type": "boolean"
+    },
+    "did_you_mean": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "hint": {
+      "type": "string"
+    },
+    "next_tool": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "available_count",
+    "available",
+    "next_tool",
+    "hint"
+  ],
+  "type": "object"
+}

First observedAug 23, 2026

TDQS

A4.7/5.0

Behavior5/5

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

The description adds substantial behavioral detail beyond the annotations: default page size of 25, maximum of 200, response budget around 64 KB, page over budget returned shorter with next_cursor, and cursor absence meaning last page. This goes well beyond the annotations' readOnly and idempotent hints.

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 dense but every clause contributes: purpose, pagination behavior, filtering rationale, and usage context with sibling differentiation. It is well structured, front-loading the core purpose before explaining paging and filters.

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?

The description covers what the tool returns, how paging works, when to use it, and how it relates to get_entity. With annotations declaring readOnly and non-destructive behavior, plus an output schema present, no critical context is missing for an agent to decide when and how to call this tool.

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 coverage is 100% and the schema descriptions are already rich, including details like 'Opaque; do not construct one' for cursor. The description mentions filter names but does not add significant parameter-level meaning beyond the schema, so it earns the baseline for high schema coverage.

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 states the tool exposes 'The instance's source registry' and that each entry includes evidence tier, reliability, and access date. It clearly distinguishes from siblings by noting that get_entity already tells which sources a claim cites, so get_sources is the way to retrieve registry entries or sample the registry.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage guidance: 'Use this when you need the registry entry behind a citation, or a sample of the whole registry to judge the corpus before trusting it'. It also points to get_entity as the alternative for knowing which sources a claim cites, and suggests filters to avoid unnecessary paging.

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

All Agent Reliability 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.