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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description adds real value by disclosing the 100-record cap, the account-access requirement, and the fact that it neither restores nor mutates the scene. It does not cover failure modes (e.g., what happens with no account or no checkpoints), which keeps it from a 5.

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?

Front-loaded with the identity ('App-only adapter for the history list') and only four sentences long, each contributing routing or constraint information. The 'does not restore or modify' clause partially restates destructiveHint=false, a small redundancy, but it also frames what the tool isn't, which aids selection.

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 one trivially constrained parameter, no output schema, and rich annotations, the description covers identity, scope cap, auth prerequisite, exclusions, and alternatives. The only gap is that the shape of the 'view.history payload' is named but not characterized, so an agent knows where results land but not what fields to expect.

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?

There is a single optional parameter with 100% schema description coverage and a const constraint of 'list', so the schema already carries the semantics. The description repeats it ('action, when supplied, must be list') and adds the useful fact that it may be omitted, but nothing beyond that. Baseline 3 applies when the 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 verb and resource ('Reads up to 100 scene-checkpoint records') and its destination ('returns them in the panel view.history payload'). It explicitly separates itself from siblings scene_checkpoints (model-facing) and view_restore (panel restore flow), so an agent can distinguish it without opening any schema.

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 routes the agent away: 'Models should use scene_checkpoints for history operations,' and clarifies when the panel uses view_restore instead. It also states the exclusion condition ('does not restore a checkpoint or modify the scene'), which is a genuine when-not-to-use statement.

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