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

Beyond the annotations, the description details the catastrophic consequences (irrevocable removal of Git data, LFS, issues, PRs, and settings) and provides crucial operational context regarding backups and required administrative scopes. This disclosure of the 'what' and 'how' of the data loss is highly transparent.

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?

Despite its dense content, the description is maximally efficient. Every sentence provides a unique piece of critical operational information (permanence, irreversibility, prerequisite, data scope), and the most severe consequences are front-loaded.

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 that this is an irreversible, high-impact administrative action, the definition is exceptionally complete. It specifies prerequisites, required permissions, the scope of deletion (all repository artifacts), and the expected return structure, leaving no critical functional detail for the agent to guess.

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?

While the schema is 100% covered, the description adds necessary safety context. Specifically, it clarifies that the 'confirm' parameter must be the repository's 'full name (owner/name)', adding a validation layer beyond the basic string type definition in 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 explicitly states the function: to 'PERMANENTLY delete an already-deleted repository now'. It clearly defines the operational difference between this action and simply using a deletion tool, specifying that it bypasses the 'restore window'. This direct comparison with the prerequisite action of `merjax_delete_repo` differentiates it strongly.

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?

The usage constraints are precise: it explicitly states, 'Only works on a repository already deleted with merjax_delete_repo'. This provides immediate and clear boundaries for when the tool is applicable and when it is not, avoiding common usage errors.

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