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

Goes well beyond the destructiveHint/readOnlyHint annotations by disclosing the runtime effect ('the bot stops using it at once'), irreversibility ('Cannot be undone'), the required role, and the two-step flow. These are exactly the consequences an agent needs before calling a destructive tool.

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?

Front-loaded with the destructive effect, then the alternative, then the procedural/role constraints. Telegraphic fragments ('Two steps. Editor or above.') are dense but borderline ambiguous as to whose editor role and what the two steps are.

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, non-idempotent, open-world delete with no output schema, the description covers effect, reversibility, alternative path, permission, and confirmation requirement. Nothing material is missing 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 coverage is 100% and each param is documented there, including the confirm_token handshake. The description only alludes to it as 'Two steps' without naming parameters, so it adds little beyond the schema; baseline 3 applies.

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+resource ('Delete one document from the knowledge base') and immediately names the sibling to use instead for corrections (dosai_edit_knowledge_document), so it is distinguishable from update/edit/read knowledge tools without opening a 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?

Explicitly routes the agent: use this to remove, use dosai_edit_knowledge_document to fix text. Adds the permission floor ('Editor or above') and the two-step confirm pattern, both of which gate correct invocation.

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