Delete a knowledge document

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

Annotations already flag this as destructive (destructiveHint=true, readOnlyHint=false, idempotentHint=false), so the safety profile is covered. The description goes beyond the annotations by specifying the exact scope of destruction (the document and its chunks) and the immediate consequence for Mira's answering behavior. No contradiction exists between description and annotations.

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 short sentences with the action ('Remove one document') front-loaded and the consequence as the second sentence. Neither sentence is redundant with the title or schema; both earn their 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?

The output schema removes the need to describe return values, and annotations carry the destructive-safety signal. The description supplies the remaining decision-relevant facts: what is deleted (document + chunks) and the immediate effect on Mira. Minor omissions (explicit irreversibility, ID provenance) are implied or made obvious by the sibling list_knowledge_documents, so the description is complete enough for a one-parameter delete tool.

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 schema provides only the bare fact that documentId is a required string (0% description coverage), so the description must help. It adds that the ID targets a single knowledge-base document, but it does not explain how to obtain the ID (e.g., from list_kknowledge_documents), its format, or behavior for an invalid/unknown ID. The parameter name is largely self-explanatory and the description's 'one document' clarification provides modest value.

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?

The description names a specific verb ('Remove') and an exact resource — 'one document (and its chunks) from the knowledge base' — so an agent knows precisely what action this triggers. It reads unambiguously as a deletion operation, which sets it apart from retrieval siblings like list_knowledge_documents and search_company_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?

The second sentence ('Mira stops answering from it immediately') conveys the functional effect, which implies the intended use: permanently cutting a document out of what Mira answers from. However, the description gives no explicit when-to-use guidance, no exclusions, and no mention of alternatives (e.g., whether any disable or unlink option exists). Usage is implied rather than stated.

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