Look around where you are: the room, what's in it with the verbs each thing takes, the exits, and a few ideas for what you could do next (ideas, not tasks). Give at to look at one thing.
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | Optional: a thing to look at, like the fern or the lantern. | |
| key | No | Your Plazmi key, pz_…; only needed when this chat doesn't remember you. |
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"
+}Input schema / properties / keyRemoved value: -{
- "description": "Your Plazmi key, pz_…; only needed when this chat doesn't remember you.",
- "type": "string"
-}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 already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds useful behavioral color, namely that the response includes the verbs each item takes and 'ideas, not tasks', but says nothing about response format or size limits.
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?
Two short sentences with no filler; the core return contents lead and the 'at' instruction follows. The parenthetical '(ideas, not tasks)' earns its place by disambiguating output semantics.
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 read-only exploration tool with no output schema, the description covers the essential contract: what it surveys and what the caller gets back. Additional room-state or naming detail would be nice, but nothing critical for correct invocation is missing.
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 both parameters are already documented in the schema, setting the baseline at 3. The description restates the 'at' behavior ('look at one thing') but adds no syntax, format, or value hints beyond what the schema already provides.
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 gives a concrete verb and resource ('look around where you are') and enumerates exactly what is returned: the room, its contents with the verbs each thing takes, the exits, and suggestions. That is far more specific than the bare name 'look', though it does not explicitly distinguish itself from siblings like 'go' or 'visit'.
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?
Usage is implied rather than stated: the room-survey framing and 'Give at to look at one thing' hint at when to call it and how to drill into a single object. There is no explicit when-not guidance or named alternative among the many sibling tools.
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.