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

Annotations already convey destructiveHint=true, readOnlyHint=false, and idempotentHint=true. The description adds crucial context beyond annotations: 'Deletes the document record and its embeddings; not reversible' – explicitly stating irreversibility and what gets removed. It also lists auth errors (401/403, 404) which informs the agent of failure modes. This is valuable extra behavioral detail that is consistent with 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?

The description is three sentences with no redundancy. It front-loads the core action and then appends auth/error/reference details in a logical flow. Every sentence serves a purpose: primary action, irreversibility, auth/errors, and related tool. No fluff.

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 2 params and no output schema, the description covers the essential operational aspects: auth modes, error codes, irreversibility, and how to obtain the required `docId`. It doesn't describe the response format, but that's minor for a delete operation and not required given the annotations. The description is sufficiently complete for an agent to invoke correctly.

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%, so both `appId` and `docId` are already documented in the schema. The description reinforces that `docId` is the key parameter and points to `ethora-sources-docs-list-v2` as its source, but it does not add new semantic meaning beyond the schema. The baseline of 3 is appropriate because the description adds only marginal value over the schema.

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 states a specific verb ('Remove') and resource ('document from RAG sources') and explicitly identifies itself as the 'app-token / B2B variant of `ethora-sources-docs-delete`', which clearly distinguishes it from the sibling tool. The agent knows exactly what action it performs and how it differs from the non-v2 version.

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 clarifies when to use this tool by detailing auth modes ('app-token mode OR B2B mode with an explicit `appId`') and notes it is a variant of `ethora-sources-docs-delete`. It also points to `ethora-sources-docs-list-v2` for obtaining the `docId`. However, it does not explicitly state when not to use this tool (e.g., for other source types) or mention alternative deletion tools, so it stops short of full exclusion guidance.

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