state_prune

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

Annotations declare readOnlyHint=false and idempotentHint=true but say nothing about the safety posture. The description adds real value by disclosing that the operation is dry-run by default and only mutates when confirm=true, which is the single most important behavioral fact for a destructive tool. It stops short of stating reversibility, blast radius (all workspaces vs one), or what a dry-run returns.

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, zero filler, with the core action first and the safety-critical default immediately after. Nothing is buried or redundant.

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 two-parameter destructive tool with no output schema, the description covers the action, the cutoff, and the safe-default behavior adequately. The remaining gaps are scope of deletion and what dry-run output looks like, which are useful but not blocking for correct invocation.

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 the schema already defines both confirm and max_age, including the dry-run default, so the description largely restates structured data. The phrase 'records older than max_age' does add a small amount of meaning by fixing the cutoff direction, but otherwise the schema carries the load.

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: 'Prune old agent state checkpoints.' An agent can tell this is a bulk cleanup operation rather than a read or write of a single record. It does not, however, distinguish itself from the sibling state_maintain, which plausibly overlaps in intent, so differentiation is incomplete.

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 gives concrete guidance on the confirm flag (defaults to dry-run; pass confirm=true to actually delete), which tells the agent how to invoke it safely. It gives no guidance on when to prefer this over state_maintain or state_doctor, and no preconditions about which checkpoints are eligible.

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