latexmk_watch_start

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

With no annotations, the description carries the burden. It discloses the background nature, auto-recompile behavior, and the session_id return value, which are crucial for an agent to understand the tool's side effects and lifetime. However, it could add more detail about stopping the process or potential side effects like build artifacts.

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?

Single sentence, information-dense, and front-loaded. No wasted words. Balances specificity with brevity.

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 tool that starts a background process, the description gives the essential facts: it's a watch, it auto-recompiles, and it returns a session_id. The parameters are covered by the schema. It doesn't explain the full lifecycle, such as how to stop it, but the sibling tools provide that context. Overall adequate for invocation.

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?

The schema already covers two of three parameters with descriptions (file_path and working_dir) and the engine has an enum and default. The description itself adds no extra parameter meaning, but the schema coverage is 67%, so the description isn't required to compensate fully. The engine's semantics are self-evident from the enum.

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 'Start' and names the specific resource ('background latexmk watch process (-pvc)') with the key behavior 'recompiles automatically on file changes'. It also states the return value, clearly distinguishing it from siblings like latexmk_compile or latexmk_watch_stop.

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 conveys the use case: continuous recompilation on file changes. However, it does not explicitly mention alternatives or exclusions, such as 'use latexmk_compile for one-shot builds', though the context of siblings makes this inferable.

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