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

Annotations already declare destructiveHint, non-idempotent and open-world, so the bar is lower, yet the description adds real consequences: 'approved' submits to the employer using the tailored CV and the answers auto_apply_get reveals, while 'declined' stops it permanently. The remaining gap is that it doesn't say what happens if the status is not pending_review or what a successful response contains.

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 sentences, front-loaded with the precondition before the two outcomes. The dense second sentence with semicolon-joined clauses is slightly harder to parse but every clause carries information about behavior.

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 two-parameter mutation with no output schema, the description covers the precondition, both outcomes, and the irreversibility of a decision. What is missing is the error case (wrong status) and any confirmation of what the call returns, which are minor for this complexity level.

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 50%: job_slug is documented in the schema, but the decision enum carries no schema description. The description compensates by explaining precisely what each enum value does, which is the more important semantic gap to close.

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 ('Record the review'), the exact resource (an automatic application whose status is pending_review), and the two possible outcomes with their consequences. An agent can distinguish this from auto_apply_get, auto_apply_retry and auto_apply_cancel from the text alone.

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?

It gives a clear precondition (the application must be in pending_review) and a constraint ('One decision per attempt'), which implies no retry. It does not explicitly name auto_apply_retry as the path once a decision is recorded, so the routing guidance stops just short of a full when/when-not statement.

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