Go back one step

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

No annotations are provided, so the description carries full burden. It discloses the format-support constraint and returns the new observation, which is useful behavioral context. However, it doesn't state what happens if unsupported (error message? no-op?), whether back at the start is a no-op, or whether the action is idempotent.

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 concise sentence with the key constraint (format support) front-loaded and return behavior appended. No waste, though the parenthetical engine reference slightly interrupts flow.

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 simple two-param undo tool with no annotations and no output schema, the description covers the essentials: what it does, when it works, and what it returns. But it leaves out error behavior and edge cases (e.g., already at start), which an agent would need to call it correctly in all cases.

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 description coverage is 100%, so both parameters are documented in the schema. The description adds no meaning beyond what's there, mentioning only the format return type. Baseline 3 when schema does the heavy lifting.

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 action ('undo the last passage navigation') with the resource (story navigation). It names the underlying engine call (SugarCube: Engine.backward), clarifying exactly what happens. It does not explicitly distinguish itself from siblings like restart or load_state, though 'undo last passage' is fairly distinct.

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?

The description implies when to use it (to undo a navigation, and only when the story format supports it), but doesn't name alternatives or state when not to use it. The format-support caveat is a helpful condition, but no sibling routing is provided.

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