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

Annotations already flag the tool as destructive (destructiveHint=true), and the description reinforces this by framing it as overriding letX's automatic engine selection. It adds useful context beyond annotations: the tool exists to correct an automatic guess and the choice of compiler is tied to document feature requirements. No contradiction with annotations.

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 sentences, each earning its place: main action with valid values, concrete selection rules, and a clear 'when to avoid' signal. Information is front-loaded and free of fluff.

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 simple tool with two parameters, no output schema, and annotations covering the destructive nature, the description is complete. It covers purpose, valid input values, selection criteria, and when to call. Nothing needed for correct invocation 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?

Input schema already documents both parameters with 100% coverage, so the baseline is 3. The description adds substantive value by mapping compiler values to concrete use cases such as fontspec, unicode-math, polyglossia, xeCJK, and \directlua, helping the agent choose the right value. It doesn't add much for project_id, but that parameter is trivially sourced from list_projects.

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 and resource: 'Choose which TeX engine a project builds with' and enumerates the exact options (pdflatex, xelatex, lualatex). It clearly differentiates from sibling compile tools by focusing on build settings rather than compilation. The purpose is unambiguous and distinct.

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?

Explicitly provides when-to-use guidance: xelatex/lualatex for fontspec, unicode-math, polyglossia, xeCJK; lualatex for \directlua or luacode. It also states when not to call it, since letX auto-detects on creation and this tool is only for overriding that guess. This is model usage guidance.

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