memory_prune

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

With no annotations, the description carries the full behavioral burden. It discloses that this is destructive and that confirm=true is required as a guard, but says nothing about irreversibility, permission requirements, scope (all workspaces vs. current), or what 'expired' means operationally.

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 short sentences, front-loaded with the destructive scope before the prerequisite. No filler.

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 an irreversible bulk-deletion tool with no annotations and no output schema, the definition leaves too much unstated: recovery options, affected scope, and the meaning of 'expired' are all missing.

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 a single parameter with 0% schema coverage, so the description must compensate. 'Requires confirm=true' does explain that the boolean must be set to true for the call to proceed, which is the key semantic — but it omits the default/behavior when false.

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 ('Delete') and a precise scope: expired memories and completed handoffs. This distinguishes it from the sibling memory_delete, which presumably targets individual memories, though the description never names that distinction explicitly.

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 only guidance is the confirm=true prerequisite. There is no statement of when to prune versus calling memory_delete or handoff_complete, nor any warning about the conditions under which pruning is appropriate.

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