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

With annotations already declaring destructiveHint=true and idempotentHint=false, the description goes beyond them by detailing the cascade (PDF deletion, broken links), irreversibility of spent generation, and specific error codes ('not_found', 'cannot_delete_active', 'cannot_delete_only'). This is exactly the kind of behavioral context that annotations cannot convey.

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 a single, tightly packed sentence with zero waste, front-loading the permanent deletion and cascade effects, then the irreversibility, then the error codes. Every clause adds distinct value.

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 a destructive mutation with annotations covering safety, an output schema exists (so return format need not be explained), and one required parameter, the description is nearly complete. The only minor gap is that it does not mention any alternative recovery path (e.g., undo), but that may be covered by sibling tools like restore_resume_revision.

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% and the description does not explicitly explain the 'resume_id' parameter, but it does contextualize the input by referencing how to obtain it ('as returned by list_resumes' is in the schema anyway). The description's focus on error conditions and cascade effects implies the parameter's role without adding format or origin details 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 states a specific verb (Permanently delete) and resource (a resume), and immediately differentiates cascade behavior (PDF files deleted, links stop working) from siblings like archive_vacancy or close_resume_link. This is far more specific than the title alone and leaves no ambiguity about what the tool does.

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 description clearly establishes the destructive, irreversible nature and the constraints (cannot delete active resume, cannot delete only resume), which implicitly tells the agent when NOT to use it. However, it does not explicitly name an alternative (e.g., archive_vacancy, restore_resume_revision, or rename_resume) for users who want to preserve data, leaving full when-to-use guidance partially inferred.

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