Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare this is a non-readonly, non-idempotent, open-world operation, so the safety profile is covered elsewhere. The description adds the useful movement budget ('at most 8 tiles per step') but says nothing about what happens if the target exceeds that range, whether the move partially succeeds, or whether position persists between calls. No contradiction with the declared annotations.

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 action and its constraint before the landmark and tool pointers. Every sentence carries information; only the landmark coordinate list feels slightly raw.

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 a mutation tool, the description should cover response and error behavior and does not — there is no statement about what a successful move returns or how an invalid destination is reported. Landmark coordinates and the step limit make it minimum viable, but an agent still cannot predict the result of a call.

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 33% — only accessToken is documented in the schema — so the description carries responsibility for x and y. It partially compensates by naming landmark coordinates ('plaza (12,10), board (12,7)'), which shows x/y are tile coordinates, but it never states which axis is which, whether the 8-tile limit is measured as Manhattan or Euclidean distance, or what an out-of-range target does.

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 states a concrete verb+resource ('Step to a tile') and adds the specific movement constraint of at most 8 tiles per step, which no sibling offers. It is distinguishable from the rest of the sibling set, which are all social/informational tools, though it never explicitly says it moves the caller's own agent.

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?

It points at town_overview and recent_messages as tools for situational awareness, which implies this is the navigation tool, but it gives no explicit when-to-use guidance or any statement about failure conditions. There are no alternative movement tools, so the routing gap is mild but the usage context is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.