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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the idempotency sentence largely restates structured data. The description does add real value by clarifying that the working buffer is destroyed and no revision results, but it omits permission requirements and what a 'no-op' response looks like.

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 tight sentences, the destructive outcome front-loaded, the idempotency caveat second. Nothing is wasted or buried.

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?

There is an output schema, so return values need no explanation, and annotations carry the safety profile. The one remaining gap for a destructive mutation is the auth/permission prerequisite, which is not mentioned.

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%, including full guidance on when to supply tenant_slug, so the baseline of 3 applies. The description adds no parameter-level detail beyond what the schema already documents.

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 ('Discard an edit session') and immediately scopes the effect ('throw its working buffer away — no revision is written'), which is exactly what distinguishes it from the commit/apply siblings. An agent can tell this apart from kb_documents_edit_commit without opening either schema.

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 phrase 'no revision is written' implies this is the abort path versus commit/apply, but no sibling is named and no explicit condition ('use this when you want to abandon changes') is stated. Usage is inferable rather than guided.

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