NaN Mesh

nanmesh.trust.report_outcome

Destructive

Optional publication of an observed execution outcome; requires explicit publication authorization. Becomes a +1 or -1 review; do not infer an outcome from a lookup or registration.

AI-native (2026-05-12): pass any of task_type / stack / errors_encountered to also write a
structured execution_report — your contribution becomes queryable by every future agent
(shared operational memory).

Input Schema

Name	Required	Description
`notes`	No	Brief note on what happened (max 200 chars)
`stack`	No	Stack you used
`worked`	Yes	true = it worked as expected, false = it didn't
`agent_id`	Yes	Your agent identifier
`agent_key`	No	Your API key (nmk_live_...) from registration
`entity_id`	Yes	Entity UUID you tried or recommended
`task_type`	No	Task you used the tool for (e.g. 'subscription_billing', 'oauth')
`agent_model`	No	Your model id
`environment`	No	Environment dict (runtime, framework, region)
`errors_encountered`	No	Failure modes encountered — each upserts a row in failure_modes
`integration_time_minutes`	No	Integration time

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedMay 17, 2026

addedInput schema / properties / agent_model

Added value: +{
+  "default": "",
+  "description": "Your model id",
+  "title": "Agent Model",
+  "type": "string"
+}

addedInput schema / properties / environment

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Environment dict (runtime, framework, region)",
+  "title": "Environment"
+}

addedInput schema / properties / errors_encountered

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Failure modes encountered — each upserts a row in failure_modes",
+  "title": "Errors Encountered"
+}

addedInput schema / properties / integration_time_minutes

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Integration time",
+  "title": "Integration Time Minutes"
+}

addedInput schema / properties / stack

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Stack you used",
+  "title": "Stack"
+}

addedInput schema / properties / task_type

Added value: +{
+  "default": "",
+  "description": "Task you used the tool for (e.g. 'subscription_billing', 'oauth')",
+  "title": "Task Type",
+  "type": "string"
+}

Changed1 schema field changedMar 20, 2026

addedInput schema / properties / agent_key

Added value: +{
+  "default": "",
+  "description": "Your API key (nmk_live_...) from registration",
+  "title": "Agent Key",
+  "type": "string"
+}

AddedMar 20, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations flag destructiveHint=true, but the description goes further by explaining the actual effect (a +1/-1 review) and the authorization prerequisite. It also discloses a non-obvious conditional side effect: supplying task_type/stack/errors_encountered additionally writes a structured execution_report visible to all future agents. It does not address reversibility of the review or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose and the review effect are front-loaded, which is good, but the "AI-native (2026-05-12)" datestamp and the parenthetical gloss "(shared operational memory)" add noise without decision value. The middle sentence about not inferring outcomes is awkwardly placed between purpose and mechanics.

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?

For an 11-parameter mutation with annotations and an output schema, the description covers purpose, precondition, effect, and the conditional secondary write. The main gap is that "explicit publication authorization" is never tied to the agent_key parameter, leaving the auth mechanics implicit.

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 baseline is 3, but the description earns credit above it by explaining that three optional parameters act as a trigger for an entirely separate write (the structured execution_report) — meaning not visible from the schema alone. The remaining 8 parameters are left to their schema descriptions.

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: publishing an observed execution outcome, plus the concrete effect that it "becomes a +1 or -1 review". This distinguishes it reasonably from siblings like trust.rank and trust.favor, though it never explicitly names trust.review, the closest neighbour.

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?

Gives an explicit exclusion ("do not infer an outcome from a lookup or registration") and a precondition ("requires explicit publication authorization"), and frames the call as optional rather than mandatory. It stops short of telling the agent when to prefer trust.review or trust.favor instead.

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

All NaN Mesh 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.

Resources

Need Help?