Mnemom — Trust Ratings for AI Agents

search_reputation_directory

Read-onlyIdempotent

Resolve an agent name or id-prefix to a real agent_id over the PUBLIC reputation directory (only agents whose reputation visibility is public). Zero-auth. The arriving-agent entry point: discover a concrete agent_id, then call get_reputation / verify_reputation on it.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`q`	No	Name search (ilike) or agent-id prefix match.
`page`	No	1-based page number for pagination. Default 1.
`sort`	No	Result ordering. Default "score" (highest-rated first); other supported keys order by recency or name.	score
`grade`	No	Filter to one grade (e.g. `AAA`, `B`, `NR`).
`per_page`	No	Number of results per page. 1–100, default 20.
`confidence`	No	Filter to agents at a given reputation-confidence level (driven by how much evidence backs the score).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`page`	Yes
`total`	Yes
`agents`	Yes
`per_page`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 27, 2026

addedOutput schema / $defs / ReputationScore / properties / checkpoint_accounting / properties / re_evaluated

Added value: +{
+  "description": "How many of the agent's checkpoints carry each kind of re-evaluation annotation (counted over `total`, not the analyzed subset). Observability only — these are not an exclusion bucket and do not enter the score arithmetic. Absent on scores computed before this breakdown existed.",
+  "properties": {
+    "corrected_clear": {
+      "description": "Checkpoints explicitly corrected to `clear` (`re_evaluation_metadata.corrected_verdict = 'clear'`).",
+      "type": "integer"
+    },
+    "corrected_non_clear": {
+      "description": "Checkpoints corrected to a NON-clear verdict — a cross-turn escalation or a reviewer reclassification to `review_needed`/`boundary_violation`. These count against the score per the correction, not as exonerations; a non-zero value is why this agent's score differs from the pre-MNE-2156 calculation.",
+      "type": "integer"
+    },
+    "resolved_no_correction": {
+      "description": "Checkpoints re-evaluated with NO recorded correction — the trust-recovery convention, scored as `clear`.",
+      "type": "integer"
+    }
+  },
+  "required": [
+    "corrected_clear",
+    "corrected_non_clear",
+    "resolved_no_correction"
+  ],
+  "type": "object"
+}

Changed4 schema fields changedJun 12, 2026

addedInput schema / properties / confidence / description

Added value: +"Filter to agents at a given reputation-confidence level (driven by how much evidence backs the score)."

addedInput schema / properties / page / description

Added value: +"1-based page number for pagination. Default 1."

addedInput schema / properties / per_page / description

Added value: +"Number of results per page. 1–100, default 20."

addedInput schema / properties / sort / description

Added value: +"Result ordering. Default \"score\" (highest-rated first); other supported keys order by recency or name."

First observedJun 12, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. The description adds key behavioral info: the tool only searches agents with public reputation visibility, requires zero authentication, and returns agent_ids. No contradiction with annotations.

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?

Two sentences, front-loaded with core action, followed by usage guidance. No redundant words. Every sentence earns its place.

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?

Covers purpose, scope (public directory), auth requirement, and next steps. With an output schema present, the description doesn't need to detail return format. Minor gap: does not explicitly state that results are paginated, but schema covers pagination params. Overall good completeness.

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?

All 6 parameters have descriptions in the schema (100% coverage), so the description adds no new param-level detail. It provides context for the 'q' parameter ('name or id-prefix') but that is already in the schema. Baseline 3 is appropriate.

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 clearly states 'Resolve an agent name or id-prefix to a real agent_id over the PUBLIC reputation directory', using a specific verb and resource. It distinguishes from siblings like get_agent (requires id) and list_agents (different scope), and positions itself as the entry point for discovering agent IDs.

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 explicitly tells when to use this tool: as the entry point to discover a concrete agent_id, then delegate to get_reputation/verify_reputation. It also notes 'zero-auth', setting expectations. This provides clear guidance on alternatives and preconditions.

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

All Mnemom — Trust Ratings for AI Agents 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.