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

Despite annotations covering write/idempotency, the description adds substantial non-obvious behavior: trace links are marked broken and shown as gaps, restoring in-app heals them, review state blocks the call, and archiving is idempotent. This is richer than the annotation set and not derivable from it.

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?

Packed with actionable facts and front-loaded with the core action, but several clauses (trace-link healing, deletion policy) read as a run-on; a slight trim would improve density without losing content.

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?

Covers operation, side effects, failure modes, idempotency, lifecycle limits (no delete by agents), and a recommended usage scenario, fully sufficient for a one-parameter mutation tool with no output schema.

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% and the single parameter (documentId UUID) is fully documented; the description adds no per-parameter detail. Baseline 3 is appropriate.

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 the specific verb+resource (archive a document) and anchors it to a known app action ('as the app's Archive action does'), which grounds the semantics beyond the bare name.

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?

Gives explicit preconditions and exclusions: refused under review, no-op if already archived, agents cannot delete, and a concrete use case ('retire a superseded document after replacing it'). An agent knows when and when not to call it.

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