Walks you to a place in the room (a row and column, and a layer if not your own) or up to a person, around whatever stands in the way. Returns once you are there, or stopped.
| Name | Required | Description | Default |
|---|---|---|---|
| row | No | ||
| layer | No | ||
| column | No | ||
| person | No | A name, as look gives it. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only say readOnlyHint=false and destructiveHint=false, so the description carries the real burden and delivers meaningful behavior: it pathfinds 'around whatever stands in the way' and returns either on arrival or when stopped. It does not say what causes a stop (blocked path, permission) or whether the walk can be interrupted.
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?
A single, well-front-loaded sentence that pairs each target type with its qualifier and ends on the termination condition. No filler or redundancy.
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 and 4 loosely-constrained parameters (0 required), the description adequately covers the target forms and the return condition. The main residual gap is disambiguating person versus row/column/layer and stating what 'stopped' means.
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 only 25% (only 'person' is documented), so the description has to compensate, and it largely does: it explains that row and column are needed, that layer applies only when the target is not your own layer, and that a person is an alternative target. It still leaves the mutual exclusivity of person vs. row/column and the coordinate ranges to inference.
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 specific verb (walks) and its two target kinds (a row/column/layer place, or a person), which separates it from travel/use_door/leave. It is clear about the action, though it never explicitly contrasts itself with the sibling movement tools.
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 only implied: 'Walks you to a place in the room ... or up to a person' tells you it is intra-room movement, but there is no explicit when-to-use versus travel, use_door, or leave, and no stated prerequisites or failure conditions beyond 'or stopped'.
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.