download_file

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

Annotations already declare readOnlyHint=falseepa and openWorldHint=true, so the agent expects side effects. The description adds that the tool writes files locally, but it does not disclose important behavioral details such as whether existing files are overwritten, whether directories are created, or what happens on failure. It adds some value but not a full behavioral picture.

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?

One tight, front-loaded sentence states the action and then cleanly enumerates the two supported source types. There is no filler, and every phrase contributes to the agent's decision-making.

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 5-parameter download tool, the description gives the critical selection logic and the provenance of fileId, and the schema covers the target directory default and course format. It does not mention authentication requirements or the return value, but no output schema exists and the primary invocation patterns are sufficiently covered.

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?

The schema only documents dir and course (40% coverage), while topicId, assignmentId, and fileId are bare integer fields. The description compensates by grouping them into two meaningful invocation modes and by establishing that fileId is obtained from get_assignment. This adds semantic meaning beyond the raw schema, though not every parameter relationship is fully elaborated.

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: 'Save a file locally' and then disambiguates exactly which source payloads count: a content topic (topicId) or an assignment attachment (assignmentId + fileId). This clearly distinguishes it from sibling content-reading tools like get_content, read_content, and search_content.

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?

It gives explicit conditions for choosing between the two valid invocation modes: use topicId for content topics, or assignmentId + fileId for assignment attachments. It also tells the agent where fileId comes from ('from get_assignment'). It does not explicitly state when not to use the tool or compare it to an alternative download tool, so it stops short of a 5.

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