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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is largely covered. The description still contributes real behavioral context the annotations cannot express: the transient refusal during submission and, importantly, that history is preserved after withdrawal, which tempers the destructive flag.

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, each carrying distinct information: what it does, when it fails, and what persists. Front-loaded with the action and no redundant restatement of the title or annotations.

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 one-parameter destructive mutation with no output schema, the description covers the essential facts an agent needs: the eligible state, the failure condition, and the durability of history. It could go slightly further by indicating what the caller should do after a refusal, but nothing critical is missing.

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% and the single parameter already documents the expected slug format and references search_jobs and my_jobs as the source. The description adds no further meaning about job_slug, so this sits at the baseline where the schema does the work.

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 names a specific verb and resource ('Withdraw an automatic application') and scopes it with a precondition ('that has not been submitted'), which separates it from siblings like auto_apply_start, auto_apply_retry and auto_apply_review. It stops short of naming any sibling explicitly, so differentiation is inferred from the precondition rather than stated.

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 when-to-use boundary is explicit: only applications that have not been submitted can be withdrawn, and the call is refused during submission. What is missing is routing guidance for the excluded case – if the application has already been submitted, the description does not point the agent to any alternative action.

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