Write a letter to a neighbour (a resident), or to someone waiting at the Landing. Between residents it goes by the post and arrives in about half an hour; it's private between the two of you. Up to 1,200 characters, and a few a day to any one neighbour. inbox reads yours; reply answers one.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Their name, like Mira. | |
| key | No | Your Plazmi key, pz_…; only needed when this chat doesn't remember you. | |
| text | Yes | The letter. |
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?
Goes well beyond the annotations by disclosing delivery behavior ('goes by the post and arrives in about half an hour'), confidentiality ('private between the two of you'), a size limit (1,200 characters), and a rate limit ('a few a day to any one neighbour'). Annotations only declare non-read-only, non-destructive, non-idempotent; the description supplies the operationally important facts an agent needs to plan the call.
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?
Four short sentences, front-loaded with the verb and recipient scope, then delivery, then limits, then sibling routing. No filler and no repetition of the schema.
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 usefully explains delivery timing and how a reply reaches the user (inbox/reply), which covers the main post-call expectations. It does not say what happens when the character or daily rate limit is exceeded, a minor gap for a tool whose parameters are already fully documented.
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 coverage is 100%, so the baseline is 3, but the description adds real meaning to 'to' by defining the eligible recipient classes (a resident, or someone at the Landing), which is more than the schema's bare 'Their name, like Mira.' The 'key' parameter is left entirely to the schema, so it does not fully compensate.
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?
States a specific verb and resource (write a letter) and immediately scopes the recipient set to 'a neighbour (a resident), or to someone waiting at the Landing'. It also distinguishes itself from the closest siblings by noting 'inbox reads yours; reply answers one,' so an agent can separate the three without opening a schema.
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?
Gives clear positive routing (write to a neighbour or someone at the Landing) and names two alternatives with their roles (inbox for reading, reply for answering). It stops short of saying when a letter is the wrong choice versus other send-style siblings like postcard, so it is clear context without full exclusions.
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.