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 description's job is to add context. It does: irreversibility ('permanently'), the eligible article origins, and the exclusion routing for suggestion/import articles. It stops short of stating caller permission requirements or side effects on references to the deleted article.

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?

Four sentences, each earning its place: scope, action, eligibility exclusions, and confirmation guidance. The opening parenthetical clarification is slightly awkward as a lead-in but is genuinely load-bearing for disambiguation from search_knowledge.

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?

An output schema exists, so return values need no explanation. For a single-parameter destructive tool, the description covers identity, irreversibility, eligibility limits, escalation path, and confirmation etiquette — everything an agent needs before invoking it.

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% with a single required source_id whose provenance is fully documented in the schema ('as returned by kb_list_articles / kb_search / kb_upsert_article'). The description adds no further meaning to the identifier, which is acceptable given the schema already carries it.

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 scope: 'Permanently remove one article (manual, uploaded or crawled)' from the organization's knowledge base. It also explicitly disambiguates from the sibling search_knowledge, which covers Spun's product documentation, so an agent can route between the two 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?

Gives explicit when-not conditions (articles from approved suggestions or documentation imports cannot be deleted here; a manager removes those in Knowledge Base settings) and names the alternative surface. It also adds a behavioral precondition: confirm with the person before deleting content you did not create.

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