Agent Reliability

Search Agent Reliability

search

Read-onlyIdempotent

Full-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries the fields it matched and a score. BM25 relevance: each query term is weighted by how RARE it is in this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights — matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one. Use this whenever you have a question rather than an id, then follow up with get_entity.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	How many ranked hits to return, best first.
`query`	Yes	What to look for, in the user's own words. Matched against titles, questions, claim text and tags; accents and apostrophes are ignored, so 'jose' finds 'José'.

Output Schema

Name	Required	Description	Default
`total`	Yes
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 6, 2026

addedOutput schema / properties / results / items / properties / coverage

Added value: +{
+  "description": "Share of the question's information this object accounts for, weighted by term rarity. 1 means every meaningful word in the query is present; a low value with a high score means the object matched common words only.",
+  "type": "number"
+}

changedOutput schema / properties / results / items / properties / matched_fields / description

Previous value: -"Which fields the query hit: name, tags, content. Does NOT determine the score on its own."New value: +"Which fields the query hit: name, tags, questions, summary, claims. Does NOT determine the score on its own."

changedOutput schema / properties / results / items / properties / score / description

Previous value: -"Text match, weighted by where the token hits (name 3, tags 2, content 1 per query token), plus a centrality bonus of up to 0.9 for objects that other objects point at. That bonus is why two hits can share matched_fields and still score differently: the decimal is inbound edges, not text relevance."New value: +"BM25 relevance: each query term is weighted by how RARE it is in this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights — matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one."

addedOutput schema / properties / results / items / properties / x

Added value: +{
+  "additionalProperties": {
+    "additionalProperties": {},
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  "description": "Indexed instance-specific attributes, grouped by namespace — the same fields api/index.json publishes. Absent when the instance declares none.",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

changedOutput schema / properties / results / items / required

Previous value: -[
-  "id",
-  "type",
-  "name",
-  "summary",
-  "tags",
-  "evidence_tier",
-  "confidence",
-  "last_verified",
-  "canonical_url",
-  "api_url",
-  "score",
-  "matched_fields"
-]New value: +[
+  "id",
+  "type",
+  "name",
+  "summary",
+  "tags",
+  "evidence_tier",
+  "confidence",
+  "last_verified",
+  "canonical_url",
+  "api_url",
+  "score",
+  "matched_fields",
+  "coverage"
+]

Changed4 schema fields changedSep 1, 2026

addedInput schema / properties / limit / description

Added value: +"How many ranked hits to return, best first."

addedInput schema / properties / query / description

Added value: +"What to look for, in the user's own words. Matched against titles, questions, claim text and tags; accents and apostrophes are ignored, so 'jose' finds 'José'."

addedOutput schema / properties / results / items / properties / matched_fields / description

Added value: +"Which fields the query hit: name, tags, content. Does NOT determine the score on its own."

addedOutput schema / properties / results / items / properties / score / description

Added value: +"Text match, weighted by where the token hits (name 3, tags 2, content 1 per query token), plus a centrality bonus of up to 0.9 for objects that other objects point at. That bonus is why two hits can share matched_fields and still score differently: the decimal is inbound edges, not text relevance."

First observedAug 23, 2026

TDQS

A4.9/5.0

Behavior5/5

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

The description goes well beyond the readOnly/idempotent annotations by explaining BM25 rarity weighting, field-specific weights, the minimum information-share requirement, and centrality's tie-break-only role. This clarifies behaviors that an agent could not infer from annotations or schema.

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 long but every sentence carries distinct, decision-relevant information about matching and ranking. It is front-loaded with the core purpose and then deepens with mechanisms that affect result interpretation.

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?

For a search tool with nuanced relevance behavior, the description is complete: it explains what is searched, how matching handles accents, how scoring works, what breaks ties, and the expected workflow with get_entity. The output schema can handle return-value details.

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 the schema already documents query and limit. The description adds meaningful guidance about query formulation: use the user's own words, common-only terms won't qualify, and rarer terms weigh more. This improves parameter understanding beyond 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?

The description states a clear verb and resource: full-text search over the knowledge graph. It also distinguishes the tool from get_entity by framing it as the right choice when you have a question rather than an id.

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?

It explicitly says to use this whenever a question is available rather than an id, and to follow up with get_entity. This gives an agent a concrete decision rule and names the relevant sibling alternative.

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.