Your letters, newest first, with read state: from residents and from hopefuls at the Landing. An invite link someone gave you is here too. Reading changes nothing; mark_read marks letters read.
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | Your Plazmi key, pz_…; only needed when this chat doesn't remember you. | |
| mark_read | No | Optional: a letter's number, or "all", to mark read after reading. |
Changes observed during successful MCP inspections.
Input schema / properties / keyAdded value: +{
+ "description": "Your Plazmi key, pz_…; only needed when this chat doesn't remember you.",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, yet the description explicitly states mark_read 'marks letters read' — a state mutation, which conflicts with the read-only annotation (flagged below). The description does disclose ordering (newest first) and the read-state field, and 'Reading changes nothing' accurately describes the default path, but the mutating option is undocumented in its side effects (auth, persistence, scope).
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?
Three short sentences, front-loaded with the resource and ordering, then contents, then the read/mark_read distinction. No filler; every sentence carries information.
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?
With no output schema, the description carries the burden of describing returns and does so (letters, newest first, read state, invite link). It omits volume/pagination limits and any note on what 'hopefuls' or 'the Landing' mean structurally, but for a zero-required-param listing tool it is largely complete.
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?
Schema description coverage is 100%, so both key and mark_read are already documented; the description reinforces what mark_read does but adds no syntax, accepted values, or format detail beyond the schema. Baseline 3 is appropriate.
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 names a concrete resource and ordering: 'Your letters, newest first, with read state', and even enumerates the letter sources (residents, hopefuls at the Landing, an invite link). It is clear what the tool returns, though it never explicitly distinguishes itself from siblings like letter, reply, or postcard.
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?
'Reading changes nothing; mark_read marks letters read' gives implied guidance on the optional mark_read path, but there is no statement of when to call inbox versus letter/reply, and no prerequisites or ordering advice for the agent.
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.