get_paper_latex

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

Annotations mark readOnlyHint as false, and the description aligns by disclosing caching and processing side effects. It adds useful behavioral context beyond the annotations: the operation downloads, processes, caches, and returns bounded source, and it tells the agent the result is bounded rather than unbounded. It does not detail what 'safely process' entails, but this is a meaningful disclosure for a side-effecting tool.

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 with no filler. The first sentence front-loads the core behavior and constraints, and the second gives a crisp usage directive. Every piece of text earns its place, and the key differentiator ('bounded', 'use section tools') appears immediately.

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?

Given the annotations are sparse and there is no output schema, the description provides the essential behavior (returns bounded LaTeX source), the caching/processing side effects, and a usage pointer to section tools. It does not describe the output format or error conditions, but the schema fully documents the parameters and the core purpose is clear enough for correct 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?

Schema description coverage is 100%, so all four parameters (paper_id, start, max_chars, return_full_text) are already documented. The description does not need to repeat parameter details. It adds only a high-level 'bounded' concept, which is already reflected in max_chars and return_full_text, so it stays at the baseline for high schema coverage.

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 resource ('original LaTeX source'), a clear action set ('Download, safely process, cache, and return'), and a key constraint ('bounded'). It also distinguishes itself from section-level tools by explicitly directing targeted reading to section tools, helping an agent separate this from sibling tools like get_paper_latex_section and read_paper_section.

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 explicitly tells the agent to use section tools for targeted reading, which is a clear exclusion that prevents misuse. However, it does not explicitly state when to choose this tool over download_paper or read_paper, nor does it name specific section tools, leaving some inference to the agent.

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