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).
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | ||
| fp | Yes | ||
| sig | No | ||
| limit | No |
Changes observed during successful MCP inspections.
Input schema / properties / atAdded value: +{
+ "maximum": 1000000000000,
+ "minimum": -1000000000000,
+ "type": "integer"
+}Input schema / properties / sigAdded value: +{
+ "maxLength": 4000,
+ "type": "string"
+}Input schema / additionalPropertiesAdded value: +falseInput schema / properties / fp / maxLengthAdded value: +4000Input schema / properties / limit / maximumAdded value: +1000000000000Input schema / properties / limit / minimumAdded value: +-1000000000000Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses meaningful behavioral traits: messages carry offline verification, access is restricted to the key owner ('Yours alone'), and the user must prove possession of the key without sending it. With no annotations, this carries some burden, but it omits output format, pagination behavior, and failure modes.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The text is efficient, with the core purpose front-loaded and authentication details following. The signature-format sentence is dense but contains necessary information without padding. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description covers the authentication contract but not the return shape, the role of `limit`, or error semantics. An agent can initiate a call but cannot anticipate the response structure or pagination defaults.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description explicitly explains `at` as Unix seconds and `sig` as a signature over `nh-mesh-read:v1:<fp>:<at>`, and warns against sending the key. However, `fp` is only mentioned as part of the signature and never defined, and `limit` is entirely unexplained. Given 0% schema coverage, this partial compensation is helpful but incomplete.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly implies a read operation for the user's inbox ('messages that reached you') and adds the differentiator of offline verification. It does not use an explicit verb like 'list' or 'get', and it doesn't contrast with sibling mesh tools, but the purpose is reasonably unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 alternatives, nor any mention of conditions that should trigger its use. The only direction given is how to authenticate (at and sig), which is parameter-level detail, not usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.