start_application

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

With no annotations, the description carries the full burden and does substantial work: it discloses the return payload in detail, the refusal behavior for duplicate applications, and the cross-board dedup memory. It stops short of explicitly stating whether the tool performs any state changes beyond planning, but the plan-oriented wording and memory disclosure make behavior largely clear.

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?

The description is dense but information-rich, with a clear front-loaded purpose sentence followed by structured output details and the key constraint. Every sentence contributes, though the long enumeration could be slightly tightened without losing value.

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?

The description covers outputs and the anti-double-apply constraint well, but with no annotations, no output schema, and 0% parameter coverage, it leaves gaps around prerequisites (e.g., existing CVs/profiles), the role of notes, and how the returned plan is meant to be consumed alongside browser or recording tools. It is adequate but not fully complete for a complex orchestration tool.

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 0%, so the description must compensate for documenting cv_id, notes, and job_id. It only indirectly references the job and CV ('chosen CV (+alternatives)'), never mentions notes, and does not explain how cv_id interacts with selection or what notes are used for. This is a meaningful gap for a 3-parameter tool.

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 opens with a specific verb and resource: 'Begin applying to a job.' It then distinguishes this tool from likely siblings by stating it returns a comprehensive plan (URL, playbook, CV, steps, cautions) rather than merely recording an application. The anti-double-apply refusal further clarifies its unique responsibility.

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 implies when to use the tool ('Begin applying to a job') and gives a clear when-not condition ('REFUSES to create a second application for a job that already has one'). However, it never names alternatives such as check_applied, record_application, or list_cvs, leaving the agent to infer the decision boundary among siblings.

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