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

Adds real context beyond the annotations: the output is a deterministic keep/archive/drop diff with token estimates, dry_run is mandated, and background queues work rather than executing now. However, readOnlyHint=false alongside 'no content is rewritten' is only obliquely reconciled, and 'Luxury background mode queues work for the suite alarm' is too vague to tell an agent what side effect actually occurs or when.

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 first two sentences are front-loaded and efficient. The third sentence is cryptic jargon ('luxury background mode', 'suite alarm') that spends words without conveying actionable meaning.

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 a deeply nested bundle schema and no output schema, the description should carry more of the return-shape and sequencing burden. It names the diff buckets and token estimates but omits the session/auth prerequisite and how the preview leads into consolidate_apply.

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 50% and the description explains almost none of the parameters. It does not describe the session bearer requirement, the bundle's free/luxury capacity implications, or what background=true changes operationally, and dry_run=true merely repeats the schema's const.

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: preview a deterministic keep/archive/drop diff plus token estimates. Combined with 'dry run is required', an agent can distinguish it from consolidate_apply. It stops short of naming the apply sibling explicitly, which is why it isn't a 5.

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?

'Dry run is required' implies this is the preview step before consolidation is applied, but the description never says to use consolidate_apply to commit. The instructions for when to choose background mode vs. sync are only hinted at via the opaque 'suite alarm' sentence.

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