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

With no annotations, the description carries the full burden and delivers: standard is deterministic and free, saves a new version unless dryRun is true, requires files:write; deep consumes credits, verifies instruction retention, never saves on its own, requires compactions:run. Mutation behavior, idempotence-ish save semantics, and auth requirements are all disclosed.

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 dense passage but front-loaded: mode standard/default behavior and its permission come first, then deep. Every clause carries a distinct fact (cost, save behavior, follow-up tool, scope), though the run-on structure slightly hurts scanability.

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?

No output schema exists, and the description adequately covers what matters for invocation: the two modes, dryRun, permission scopes, and the post-deep-call workflow. It doesn't describe where the resulting version id or job id surfaces, which is a minor gap for a mutation tool.

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 0%, so the description must compensate. It explains mode semantics and dryRun's effect well (2 of 4 parameters), but says nothing about fileId or artifactBundleId beyond their names, leaving the two required identifiers undocumented in both schema and description.

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: 'Shorten a markdown or text prompt without losing instructions.' It is clear what the tool operates on and the invariant it preserves, though it doesn't directly contrast with a sibling that does the same shortening (rubrkit_apply_deep_compaction is presented as a follow-up, not an alternative).

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 separates the two modes, gives the default (standard), states what each mode does and whether it saves, and routes the deep path: poll the returned job, then call rubrkit_apply_deep_compaction. It also names the required scopes per mode. It stops short of stating when a caller should prefer this tool over any non-compaction sibling.

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