lemma_get_pdf

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

Describes the key behaviors beyond schema: save_to writes to an absolute path, and small files are returned base64-inline. With no annotations, this is useful, though the notion of 'small' and the exact behavior for large files without save_to remain undefined.

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 front-load the core action and then add only the parameter behaviors that matter. No filler or restatement of the 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?

For a two-parameter download tool, the description covers input and primary output paths, but the small-file/large-file ambiguity and lack of an output schema leave a small but real gap. An agent could still call it correctly in the common case, but not with full certainty about large-file responses.

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?

Every parameter is given meaning beyond its string schema: file_id is the file identifier from the first sentence, and save_to is described as an absolute path with a conditional write behavior. This fully compensates for the 0% schema description 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?

Uses the specific verb 'Download' with a file resource addressed by file ID, and the lockbox-mail example anchors it in the domain. This clearly distinguishes it from the sibling get/list endpoints that return structured data rather than a binary file.

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?

Usage is implied rather than explicit: an agent can infer 'call this when you have a file_id and need the PDF,' and the lockbox example gives one scenario. There is no explicit when-not-to-use or alternative routing, so it falls short of full guidance.

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