easy_apply_job

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

No annotations are provided, so the description carries the full transparency burden. It discloses the dry_run behavior and that submission only affects 'the first step', which is useful. However, it doesn't disclose side effects like needing to be logged in, or what happens after submission (follow-up steps, multi-step forms). The description covers the core safe behavior but leaves the lifecycle of multi-step applications unclear.

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?

Two sentences, zero wasted words. The description front-loads the primary purpose and immediately explains the critical dry_run default, making it efficient and actionable.

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?

This is a stateful action tool (submit an application) with no output schema and no annotations. The description explains the dry_run mechanism clearly, which is helpful, but for a tool that triggers a workflow with potentially multiple steps and side effects (form submission, navigation changes), more context about the process lifecycle and login requirements would strengthen completeness.

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 67%, with note and dry_run documented in the schema itself but job lacking a description. The tool description adds the crucial dry_run default behavior (dry_run=true) which clarifies the boolean's semantics beyond 'do not submit'. The 'job' parameter semantics are implied ('on a job') but not explicitly explained in the description, keeping it 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?

The description uses a specific verb+resource ('Start LinkedIn Easy Apply on a job') and clearly distinguishes the tool's purpose from siblings like save_job, get_job_applications, and search_jobs. The dry_run default behavior is clearly stated, differentiating this from simple job viewing or saving.

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 description clearly explains the dry_run default behavior and when to set dry_run=false ('submit the first step if possible'). It implies this is a mutation/action tool for applying, distinguishing it from read-only siblings like get_job or search_jobs. However, it doesn't explicitly state when NOT to use this tool or mention alternatives like save_job for later.

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