Delete Knowledge Document

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

The annotations already indicate destructiveHint=true, but the description adds important context: it specifies that the document record and its embeddings are deleted and that the operation is not reversible. It also discloses auth-related error conditions (401/403 for wrong auth, 404 for unknown appId/docId), which are not present in the structured annotations. This exceeds the annotation baseline.

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?

The description is moderately concise but contains redundancy: 'Requires: a document id from ethora-sources-docs-list-v2' and 'Related: get docId from ethora-sources-docs-list-v2' convey the same instruction twice. The layout is otherwise clear, but the duplication makes it slightly less efficient than it could be.

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 simple delete tool with only 2 parameters and no output schema, the description covers all essential aspects: purpose, authentication, required input, error conditions, and irreversibility. It omits the success response format, but that is minor given the operation's simplicity and the absence of an output schema.

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%: both appId and docId already have descriptive text. The tool-level description restates the same information (e.g., 'Get it from ethora-sources-docs-list-v2') without adding new parameter-level semantics. According to the rubric, this warrants a baseline of 3.

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 clearly identifies the action ('Remove a previously ingested document') and the resource ('from an app's RAG sources by docId'), and distinguishes it from the sibling tool ethora-sources-docs-delete by labeling it the app-token/B2B variant. This fully clarifies what the tool does and how it differs.

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 description explicitly names the prerequisite (obtain docId from ethora-sources-docs-list-v2), the supported auth modes (app-token or B2B with explicit appId), and references the alternative tool (ethora-sources-docs-delete) with the distinguishing variant label. It stops short of an explicit 'when not to use' statement, but the context is clear.

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