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

The description discloses that deletion is not reversible, that embeddings are also deleted, and that missing ids are skipped. These go beyond the annotations' `destructiveHint: true` and `idempotentHint: true`, adding specific context about what is destroyed and how idempotency is handled. It also mentions auth errors (401/403/404). No contradiction with annotations; instead it enriches them.

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 compact and front-loaded. The first sentence gives the core purpose and constraints. The second adds irreversibility and idempotent behavior. The third covers auth and errors. The fourth provides a pointer to the list tool. Every sentence adds necessary information without fluff. The structure is logical and efficient.

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 batch operation, the description covers the critical aspects: what is deleted, how many, how to obtain ids, auth requirements, error codes, irreversibility, and handling of missing ids. It does not mention the return value (e.g., count of deletions, errors), but for a deletion tool this may be acceptable. It also does not explicitly mention that the operation is asynchronous or synchronous, but given it's a batch call, it's likely synchronous. Overall, it's quite complete, with a minor gap on response details.

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% (both parameters have descriptions). The description adds significant value by clarifying that `ids` are 'source record ids' (not URL strings) and instructing to retrieve them from the list tool. It also explains the `appId` parameter's role in B2B mode and that it is ignored in app-token mode. This goes well beyond the schema descriptions, which only state 'Site source record ids' and '24-char hex appId'. The description provides essential context for correct invocation.

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 states the action: 'Bulk-remove crawled website sources (1–100) from an app in one call, matched by their source record ids.' It specifies the verb, resource, and scope, and distinguishes itself from the sibling single-delete tool by emphasizing 'bulk' and the 1–100 range. This is a specific, unambiguous purpose.

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?

Provides clear guidance on when to use this tool: for bulk deletion (1–100) as opposed to single deletion (implied by the sibling). It tells the agent how to get the ids from `ethora-sources-site-list-v2`, explains auth modes (app-token or B2B with explicit `appId`), and lists error codes. While it doesn't explicitly state 'use this instead of the non-batch version', the bulk/quantity distinction makes the usage context clear. It could have explicitly said 'for single deletion use ethora-sources-site-delete-url-v2', but the guidance is sufficient.

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