download_pdf

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

Annotations already flag destructiveHint=true, idempotentHint=true and openWorldHint=true. The description usefully implies a server-side build happens before the download, but it never explains the destructive aspect (e.g. overwriting an existing file at output_path) or what happens when compilation fails.

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?

A single front-loaded sentence with no filler, sized well for the tool. It could have spent one more sentence on the overwrite/build behavior without becoming bloated.

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?

Adequate but with clear gaps for a tool marked destructive: nothing about local file overwrite, compile failure handling, or the effect of resource_path. The rich schema covers parameters, but the write-side behavior is left implicit.

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 three parameters, including the subtle resource_path root-document selector, are already documented. The description adds nothing beyond the schema, so the baseline of 3 applies.

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?

States a specific compound verb (compile + download) and the exact resource (resulting PDF saved to a local file). It is distinguishable from 'compile' and 'download_file' in principle, but never names those siblings explicitly.

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?

There is no guidance on when to use this rather than 'compile', 'compile_with_outputs', or 'download_file', and no mention of prerequisites such as needing the project to compile successfully. The agent must infer the choice from the tool name alone.

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