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

Annotations already mark destructiveHint=true, but the description adds crucial behavioral context: the operation is a soft delete, the file moves to _archived/, and it can be restored later. The write-tier approval requirement is also an important behavioral disclosure that goes beyond structured hints.

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 terse paragraphs: the first delivers the core subject-verb-object statement, and the second supplies necessary approval workflow guidance. No filler, and the key operation is front-loaded.

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 only 2 parameters, no output schema, and no nested objects, the description covers all essential operational aspects: the action, the triggering user intent, the archival mechanism, reversibility, and the approval caveat. Nothing critical is missing for an agent to invoke this 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?

The input schema already provides 100% coverage for both slug and companyId with clear descriptions. The description's mention of 'by slug' reinforces the primary parameter but adds no new information beyond what the schema already states.

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 action ('Archive a knowledge file by slug'), explicitly clarifies it is a soft delete, and ties the tool to a clear user-intent ('when the user explicitly asks to remove a knowledge document'). This differentiates it from siblings like restore_knowledge and read_knowledge.

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 an explicit trigger condition ('when the user explicitly asks to remove a knowledge document') and detailed approval-flow guidance including when to invoke and not to re-ask. This is highly actionable and removes ambiguity about when to call the tool.

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