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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds real context beyond that: the blast radius includes 'all associated history' and deletion is 'permanent', which tells the agent what is actually lost. It stops short of stating permission requirements or that the operation cannot be undone once the credential is used.

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?

Two sentences, front-loaded with the destructive action and the two scopes; nothing is buried. The opening 'Purge Desk Data.' duplicates the name/title and earns no place, which is the only waste.

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?

An output schema exists, so return values need no explanation, and annotations carry the safety hints. For a three-parameter destructive tool the description covers the verb, both scopes, and the scope of destruction ('all associated history'), leaving nothing an agent needs to call it correctly.

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 100% and each parameter (scope, desk_key, sender_domain) is fully documented in the schema, so the baseline is 3. The description's mention of 'a specific sender domain' vs 'your entire desk' restates the scope enum without adding format, dependency, or validation detail.

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 ('purge/wipe/delete') and resource ('Desk Data', records for a sender domain, or the entire desk) and distinguishes the two operating modes. It does not differentiate from siblings, but the sibling list (draft_response, get_scoreboard, etc.) contains no overlapping purge-like tool, so differentiation is largely moot.

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?

'Use this to wipe records for a specific sender domain or permanently delete your entire desk' describes what the tool does rather than when to choose it, and there is no when-not guidance, prerequisite statement, or alternative named. The two scopes are implied as the selection criteria, which maps loosely onto the scope enum, but nothing is explicit about consequences of choosing one vs the other.

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