Bulk download a course's files

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

Annotations include readOnlyHint=true and openWorldHint=true)Skip, which already indicate the operation is safe and may have external side effects. The description adds: 'Respects the configured size limit per file' and 'skips files already on disk,' which are useful behavioral details about potential limits and idempotency. However, it does not disclose that downloads may hit the blackboard's permissions or that some files may fail silently, but given annotations cover the read-only nature, a 3 is appropriate.

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?

The description is two sentences: the first states the primary function and output organization, the second gives the use case and safety behavior. It is concise and front-loaded with pivotal information. No fluff, though it could be slightly more structured with bullets, but it is efficient.

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 tool has 4 parameters, a read-only annotation, and no output schema, the description adequately covers the tool's purpose and key behavior. It doesn't explain return values, but for a download tool, that's less critical. It could benefit from noting that the operation runs in the background or requires specific permissions, but the description is sufficient for typical use.

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 have descriptions in the schema. The tool description only adds context on the `maxFiles` and `maxNodes` defaults implicitly via 'size limit' but does not restate each parameter. Since the schema already explains each parameter well, the description adds marginal value. Baseline 3 is correct.

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 clearly states the tool's purpose: 'Walks a course and downloads every attached file to a local folder, organised by course.' It specifies the action (download), the resource (course files), and the output (local folder). It distinguishes itself from simpler file download tools like bb_download_file by indicating bulk behavior, and from other siblings by the phrase 'Use for archiving a course or grabbing all slides at once.'

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 provides explicit use cases: 'Use for archiving a course or grabbing all slides at once.' It implies contrasts: `bb_download_file` for single files, `bb_download_submission` for submissions menus. However, it does not explicitly say when *not* to use it or list alternatives by name. The guidance is clear but minimal exclusions.

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