concordance

mesh_inbox

[KEEP · internal] The messages that reached you, each carrying its own offline verification so you trust it by proof rather than by this server's word. Yours alone: prove your key — pass at (unix seconds) and sig, a signature over nh-mesh-read:v1:: made with your key (never send the key).

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": {
      "fp": "<fp>"
    },
    "name": "mesh_inbox"
  }
}

Input Schema

Name	Required	Description	Default
`at`	No
`fp`	Yes
`sig`	No
`limit`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 23, 2026

addedInput schema / properties / at

Added value: +{
+  "maximum": 1000000000000,
+  "minimum": -1000000000000,
+  "type": "integer"
+}

addedInput schema / properties / sig

Added value: +{
+  "maxLength": 4000,
+  "type": "string"
+}

Changed4 schema fields changedAug 4, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
- addedInput schema / properties / fp / maxLength
```
Added value: +4000
```
- addedInput schema / properties / limit / maximum
```
Added value: +1000000000000
```
- addedInput schema / properties / limit / minimum
```
Added value: +-1000000000000
```
AddedJul 28, 2026

TDQS

C2.8/5.0

Behavior3/5

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

With no annotations, the description carries full burden. It usefully discloses the auth requirement (sign with your own key, never send the key) and the trust model (verify by proof, not by server trust), but says nothing about pagination, error behavior, or what 'limit' does.

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?

Two sentences, reasonably front-loaded, but padded with flowery framing ('trust it by proof rather than by this server's word') and a noisy metadata tag ('[KEEP · internal]') that adds no invocation value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-param tool with no annotations and no output schema, the core purpose and auth flow are covered, but the description omits pagination/limit semantics, failure modes, and any differentiation from the mesh family, leaving real gaps.

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 0%, so the description must compensate. It richly documents two params ('at' as unix seconds, 'sig' with the exact signed string nh-mesh-read:v1:<fp>:<at>), but leaves the required 'fp' and the 'limit' parameter entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description conveys the resource (the messages that reached you) but never states a clean verb+resource pair, relying on prose ('the messages that reached you') and the tool name to imply 'read my inbox.' It also fails to distinguish this read tool from mesh siblings like mesh_map, mesh_door, mesh_post, or mesh_signable.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus the many mesh_* siblings. The only instruction given ('prove your key — pass at and sig') is parameter mechanics, not a use/don't-use condition.

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

All concordance 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.