job104_prepare_application

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

No annotations exist, so the description carries the full burden, and it discloses the most important trait explicitly: it will never press the submit button and leaves the window open for human manual confirmation. It also reveals the mechanism (a real Playwright-driven browser window) and that a screenshot is captured. Gaps remain around session/auth prerequisites, whether anything persists server-side, and what dry_run actually suppresses.

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, front-loaded with a bracketed category tag, then the workflow, then the safety rule placed last where it is most memorable. Every sentence carries information; only minor redundancy exists between '自薦信範本' and '客製推薦信'. Efficient and well ordered.

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?

Output shape is covered by the output schema, and the description covers the interaction model and the critical non-destructive guarantee, which is the main risk for a browser-automation tool. For a tool with no annotations and 0% parameter documentation, it should still address login/session state, what dry_run changes, and what happens when the named template is missing.

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 should compensate, and it only partially does: the 'open a real job window', 'switch to the specified template', and 'fill a custom letter' clauses implicitly map to job_url_or_id, template_title, and cover_letter_text. It never states that job_url_or_id accepts either a URL or a bare ID, and dry_run — the parameter most relevant to the stated safety model — is not mentioned at all.

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 chain and resource: opens a real job listing window via Playwright, switches to a specified cover-letter template, fills a custom letter, and takes a screenshot. That chain is clearly distinct from the read-oriented siblings (job104_job_detail, job104_search, job104_get_my_templates) and from analysis work. An agent can tell what this tool produces (a prepared, un-submitted application window) without opening the schema.

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 bracketed label '代填應徵' plus the human-in-the-loop framing establishes clear context for when to reach for this tool: pre-filling an application for a human to verify. There are no explicit exclusions or named alternatives (e.g., how this differs from job104_apply_analysis), so routing is implied rather than prescribed. Clear context without exclusions lands at 4.

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