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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is covered. The description adds value beyond that by stating the effect is permanent – the application cannot be resumed and the user must start over – which is exactly the consequence an agent needs before calling a destructive tool.

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 action, then the irreversible consequence, then the prerequisite. Every sentence earns its place and nothing is padded.

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, so return values need not be explained. For a one-parameter destructive tool the description covers action, irreversibility, and provenance of the session_id; it leaves unstated what happens if no application is in progress or if the session_id is stale.

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 0% and the single session_id parameter is required, so the description carries the burden. It usefully names the two sibling tools that produce a session_id (apply_for_job, list_active_applications), which is more than the schema provides, though it doesn't state the identifier's format or that it is passed as the Session-Id header.

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?

States a specific verb ('Stop') and resource ('an application that Worklittle is filling out for the user'), which cleanly separates it from siblings like delete_my_resume, apply_for_job, and check_application_status. An agent can route between stop_application, list_active_applications, and apply_for_job without inspecting schemas.

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?

Gives the prerequisite for use – the session_id must come from apply_for_job or list_active_applications – which tells the agent both when this tool applies and what must precede it. It stops short of explicit when-not-to-use guidance or contrast with a sibling cancel/resume tool, but the context is clear.

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