Forget Visual State

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

Annotations already declare destructiveHint=true, and the description adds useful specifics by listing what gets purged (vector embeddings and perceptual hashes) and that it permanently removes from storage. This goes beyond the structural hints, though it does not mention irreversibility explicitly, which is implied by the annotation.

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 a single, tightly constructed sentence that front-loads the action ('Purge') and includes only essential details. Every word contributes value, with no fluff or repetition.

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 destructive tool with one well-documented parameter and existing annotations (destructiveHint, etc.), the description is complete. It covers what action is taken, precisely what is affected, and the intended use case, making it sufficient for an agent to invoke correctly.

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% for the single parameter 'state_id', which is already described as 'ID of visual state to purge'. The description does not add extra detail beyond calling it 'specific', so the schema carries the semantic weight, meriting the baseline score 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 uses a specific verb ('Purge') and clearly identifies the resource ('a specific visual state, its vector embeddings, and perceptual hashes'). It also states the purpose ('privacy or memory reset'), which differentiates it from sibling tools like 'undo_last_visual_mutation' that imply reversible operations.

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 phrase 'for privacy or memory reset' implies a context for use, but the description does not explicitly say when to use this tool versus alternatives like 'undo_last_visual_mutation' or 'save_visual_snapshot'. There is no when-not-to-use guidance or naming of alternative tools.

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