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

Adds substantial behavior beyond the destructiveHint annotation: it enumerates the cascading records removed (leave requests, adjustments, checklist tasks, document records), says files remain in the file store, and states the manager-reassignment blocker. This is exactly the kind of consequence detail an agent needs before invoking a destructive tool.

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 front-loaded and each substantive sentence carries useful scope, precondition, or alternative information. The only clear waste is the duplicated trailing 'Free. Free.', which slightly undermines polish.

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?

For a destructive single-parameter tool with no output schema, the description covers the cascade, retained files, blocking manager condition, and non-destructive alternative. An agent has enough information to decide when not to call it and how to prepare for a successful call.

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?

There is only one parameter, and the schema already fully documents it as person_id or work email. The description does not add format or lookup guidance beyond the schema, so the 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 a specific verb and resource ('Erase a person') and immediately scopes the operation as cascading to their HR records. It also distinguishes the delete from the non-destructive alternative of setting an end_date, so an agent can tell what this tool uniquely 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?

Gives explicit when-to-use ('when they ask to be forgotten'), a blocking precondition ('Refused while they manage others: give those people another manager first'), and a clear alternative ('To keep someone's history after they go, set their end_date instead'). It even routes file deletion to files_delete instead.

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