purge_cache

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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=true. The description adds real value beyond that: it names exactly what is destroyed (whole library + SportRxiv copy) and adds a consent precondition. It does not discuss reversibility or downstream effects (e.g. SportRxiv side effects), hence not a 5.

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 scope and then the consent gate. No filler; every clause earns its place.

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, irreversible-sounding single-param tool, the description covers scope, consent gating, and shares the safety burden with annotations. It leaves some ambiguity about whether the SportRxiv deletion is propagated externally, but is otherwise complete enough to call 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 coverage is 100% and the 'confirm' parameter is already documented as 'Must be true to delete.' The description reinforces intent ('only when the user asked for it') but adds no format/syntax beyond the schema. 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 destructive verb ('Delete') and a precisely scoped resource (the user's whole football-docs paper library and the SportRxiv copy), including the destructive scope detail that distinguishes it from sibling forget_paper.

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?

Explicitly gives the gating condition for invocation: 'Call with confirm: true only when the user asked for it.' This is clear when-to-use guidance plus an exclusion, tying directly to the required parameter.

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