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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds real substance: preview/customer access stops immediately, there is no undelete, no durable receipt, no retained-answer correction, and blind retries cannot recover a lost response. That is concrete consequence disclosure an agent cannot get from the structured fields alone.

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?

Three short sentences, front-loaded with the destructive action and its scope. The final sentence about blind retry overlaps with the earlier 'no undelete / no durable receipt' clause, so it repeats rather than extends the disclosure.

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 and both parameters are documented in the schema, so the description only needs to carry behavioral risk — which it does thoroughly, including irreversibility and post-failure behavior. What is missing is a crisp statement of the prerequisite step (impact preview, operation status check) before and after invocation.

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% (agent_id and source_id each point at their listing tools), so the schema carries the parameter semantics fully. The description adds nothing about parameter format or constraints, which is acceptable but leaves this at the baseline.

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?

Specific verb (withdraws) plus resource (source and its unshared retrieval content), with the permanence qualifier that separates it from reversible source operations like source_refresh or source_text_revise. The reference to source_withdrawal_impact anchors it against the sibling that previews the same target.

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?

Naming source_withdrawal_impact implies a preview-then-withdraw workflow, and 'blind retry cannot recover a lost response' hints that source_operation_read should be used after a failure, but neither is stated as an instruction. Usage is inferable rather than explicit; no when-not or prerequisite guidance is given.

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