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

Annotations provide only readOnlyHint=false, destructiveHint=false, and idempotentHint=false. The description adds significant behavioral context: movement is a state change, pathfinding routes around walls/closed doors, detours are reported via pathCost, speed limits are checked via pathCost * gridDistance > speed, closed doors count as walls unless opened, and locked/secret doors are always impassable. This goes far beyond annotations and discloses all relevant side effects and constraints.

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?

Despite its length, every sentence earns its place. It starts with the core purpose, then flows logically through coordinate conversion, token lookup, pathfinding behavior, speed limits, and door handling. No redundancy or filler; the structure is efficient and front-loaded with the most critical usage 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?

Given the tool's complexity (pathfinding, door states, speed checks) and the absence of an output schema, the description covers all necessary details: how coordinates are computed, how to find tokenId, what the response contains (pathCost, doorsOpened), and when to defer to scene-set-door-state. An agent has everything needed to invoke the tool correctly without external knowledge.

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%, but the description enriches every parameter. It explains the coordinate system (pixels, top-left corner) and the pixel-to-grid relationship, clarifies that tokenId comes from token-list, defines canOpenDoors as only opening when user explicitly asks, and explains the result fields (doorsOpened[], pathCost). This adds semantic meaning that the schema alone does not convey.

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 specific verb and resource: 'Move a token to new coordinates', with precise coordinate semantics (pixels, top-left corner; pixel = gridCoord * gridSize). It clearly differentiates from sibling tools like token-list (to find tokenId) and scene-set-door-state (for locked/secret doors), leaving no ambiguity about what this tool does.

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?

Explicitly instructs to use token-list to find tokenId, and explains when pathfinding detours are needed (pathCost reported). It gives conditions for opening doors (canOpenDoors=true only when user explicitly asks) and for locked/secret doors (use scene-set-door-state first). This is comprehensive guidance on when and how to use the tool versus alternatives.

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