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

Goes well beyond the annotations (readOnlyHint false, openWorld true, idempotent false): it discloses the anonymous daily quota, that failed attempts don't count, how API keys raise limits, and the exact over-limit behavior (preview PDF, total_pages, plan_required, warning that must be relayed rather than silently truncating). It also states that failures return a `diagnosis` with a suggested fix and instructs the agent to retry itself instead of surfacing a TeX log — precisely the behavioral context annotations cannot carry.

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?

Long but front-loaded and sectioned with uppercase headers, so the agent can scan purpose, when, when-not, auth/pricing, and failure handling independently. Each paragraph carries actionable information (escaping rules, retry-on-diagnosis, preview relaying) rather than restating the name or schema.

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?

There is no output schema, and the description compensates by naming the return fields (PDF URL, page count, compile time) plus the conditional preview/plan_required shape and the diagnosis-on-failure shape. Combined with the auth and quota model, an agent has everything needed to call it, handle failure, and report results correctly.

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 coverage is 100%, so both parameters are already documented (including the compiler enum guidance). The description still adds non-obvious semantics: the `latex` argument must be complete, valid source the agent generates itself, with the escaping rule for % & $ # _ { } and backslash. It does not repeat the per-compiler guidance already in the schema, which is fine.

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 first sentence states a specific verb and resource (compile LaTeX source into a PDF) plus the return values. It draws a hard boundary against the nearest confusable operations (HTML-to-PDF, merge/split/compress, text extraction), so an agent can distinguish it from any document sibling 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?

Explicit three-part routing: 'USE THIS WHEN' names both the trigger (you have LaTeX source or a \documentclass and no local TeX install; or the task is a typeset-matters document like an invoice, contract, CV) and 'DO NOT USE THIS TO' names the excluded cases with the alternative family for each. Nothing is left to inference.

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