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

Although annotations already mark destructiveHint=true, the description adds essential behavioral detail: refusal conditions for dependent article_profiles, the append-only nature of consolidation_pack_observations, and the design rationale referencing PRINCIPLES.md. No contradiction with annotations.

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 appropriately sized for a tool with significant constraints. The first sentence front-loads the core action, and the subsequent paragraphs efficiently explain exceptions and design rationale without filler.

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?

Given the tool is destructive, has no output schema, and handles two distinct table types, the description covers behavior, constraints, refusal cases, and rationale well. It doesn't describe the return value/success response, but the rest is complete enough for an agent to use safely.

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?

The input schema already describes all three parameters thoroughly (100% coverage), so the description adds limited extra parameter meaning. It does add a useful mapping between the 'table' enum and the originating call, but this is modest beyond the schema.

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 clearly states it 'Undoes a create_article_profile or log_pack_observation call', naming specific verbs and resources. It also distinguishes this tool from its siblings by emphasizing that it is only for undo, not for general editing/deleting.

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?

It gives explicit usage boundaries: only within 15 minutes of confirmation, only if nothing depends on it, and never as a general edit/delete capability. It also names the alternative path: 'edit it or delete it manually in the app instead of undoing'.

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