gl_archive_purge

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

Goes well beyond destructiveHint/idempotentHint by disclosing the structural guarantee that live journal rows cannot be touched, that a purge record is left in place, that refusal is itself recorded as a data-subject response, and that purged data is unrecoverable. Contradicts nothing in the 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?

Front-loads the core action and retention condition, and the CONSEQUENCE line is useful for a destructive op. It is somewhat repetitive, restating the deletion/retention facts a second time.

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?

With no output schema, the description supplies enough behavioral context (record kept, refusal recorded, irreversibility) for safe invocation. The remaining gap is the date-range and idempotency parameter formats.

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%, so the description must carry parameter meaning; it explains reason and confirmed:true but leaves periodFrom/periodTo formats, workspaceId, and idempotencyKey undocumented. Partial compensation for a 6-parameter tool.

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 (purge archived periods) with the governing condition (OR 958f ten-year retention expired) and explicitly bounds scope to ARCHIVE data only. Among siblings like gl_archive_query, gl_archive_periods, and gl_archive_import, this is unmistakably the destructive one.

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 clear conditions for use (retention expired, confirmed:true required) and for refusal (inside the retention window). It does not name a sibling alternative for the non-destructive cases, but the exclusion logic is spelled out.

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