Apply to a job

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

Even though annotations already declare destructiveHint=true and openWorldHint=true, the description adds substantial context beyond them: submission 'cannot be recalled', it needs pre-existing materials and plan allowance, a mismatch on expectedRevision 'fences the send', and the confirmation hold is a real two-phase protocol with a token bound to identical arguments. That is exactly the behavioral texture an agent needs for an irreversible action.

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 dense sentences with the core action front-loaded and no filler; each sentence carries new constraints (preconditions, irreversibility, hold/token protocol). The middle sentence is long but every clause earns its place.

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, open-world tool with no output schema, the description covers preconditions, irreversibility, and the shape of the held result (destination, material summary, token). It stops short of describing the successful-submission outcome or failure modes, which is a minor remaining gap.

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?

With 67% schema coverage, only applicationId is undocumented in the schema. The description compensates by explaining that materials are taken at expectedRevision and that the token is bound to identical arguments, adding meaning over the schema text rather than repeating it.

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 and resource ('Submits one application to an employer') plus the key scoping detail ('using the saved materials at expectedRevision'), which distinguishes it from preparation-oriented siblings like prepare_applications and strengthen_application. It does not, however, name or exclude any sibling explicitly, so an agent must infer the boundary itself.

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 conveys implied prerequisites ('requires existing materials and plan allowance') and the two-phase hold/confirm flow, which tells the agent the call is not a one-shot. But it never says when to reach for this tool instead of alternatives such as mark_applied_offsite, cancel_apply or generate_outreach, leaving the routing decision to inference.

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