Toggle token condition

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

The description extensively discloses behavior beyond the sparse annotations: the toggling semantics, side effects on linked tokens (lands on actor and shows on all tokens), required actor permission, that removal only removes that condition's effects, that state is read back, and that level-based conditions need a system adapter. This is rich, non-obvious behavioral context that helps an agent predict outcomes and side effects.

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?

The description is dense and full of useful information, but it is a bit lengthy, covering many edge cases and examples. It is front-loaded with the primary action and then explains parameters and behaviors. While every sentence adds value, some redundancy with schema descriptions (e.g., 'active' semantics) could be trimmed. It is not overly verbose, but not as tight as it could be.

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 tool with no output schema, the description covers the main behavior, permissions, side effects, level handling, and state read-back. It is reasonably complete, though the exact nature of the returned state is vague ('The state is read back') and edge cases like invalid conditionId or unauthorized access are not addressed. Given the tool's complexity, the description provides solid coverage without being exhaustive.

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?

Although the schema already covers all five parameters and has 100% description coverage, the tool description adds value with extra examples and nuances: 'frightened 2 in Pathfinder 2e or pain level 2 in DSA5' for level, and the requirement that 'it needs an adapter for the game system that knows the levels.' It also clarifies that conditionId can come from get-available-conditions, which is not in the schema description. This surpasses a baseline of 3.

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 clearly states the action ('Set or remove a condition') and the resource ('on the actor of a token'), with examples like prone, poisoned, blinded. It identifies the main toggle behavior with 'active true sets it, false removes it, and without active it toggles.' However, it does not explicitly contrast with sibling tools such as manage-effects or pf2e-manage-conditions, so it lacks an explicit sibling differentiation.

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 gives clear operational guidance: how to use the 'active' parameter, that conditionId can be an id or name from get-available-conditions, and that linked tokens require actor permission. It provides context for correct invocation (e.g., level behavior and adapter dependency) but does not explicitly specify when to prefer this tool over alternatives or list exclusions.

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