lock

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

Discloses that the derived key is cleared and that subsequent operations need unlock. No annotations provided, so description carries full burden; it adequately covers the behavioral impact.

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, no wasted words. First sentence front-loads the primary action; second adds important context.

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?

Fully sufficient for a parameterless tool with no output schema. Covers action, consequence, and recommended usage pattern.

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?

No parameters, so baseline score of 4 applies. Description does not mention parameters (none exist), so no deduction.

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?

Clearly states 'Clear the derived key from memory' with a specific verb and resource. Distinguishes from siblings by explaining that after this, store/fetch/list/remove require unlock again.

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?

Provides explicit guidance: 'Recommended at the end of a session.' Implies context but no explicit exclusions or alternatives; siblings exist but not directly compared.

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