download_app

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

There are no annotations, so the description carries the full burden. It mentions quarantine and provenance but does not clarify what these mean for the output (e.g., is the file transformed, does it include metadata?), nor does it state authentication, return format, or any side effects. For a download tool, it does not disclose if quarantine files are downloaded in a special form or if provenance is included as metadata. This leaves significant gaps.

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 a single sentence that is concise and front-loaded with the action. It includes relevant qualifiers ('persisted allowed candidate', 'quarantine and provenance') without excessive wordiness. However, it could be slightly clearer, but overall 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?

With 2 parameters, 0% schema coverage, no annotations, and no output schema, the description needs to compensate. It mentions quarantine and provenance, which are output-related, but does not explain the output format, file location (out parameter), or any constraints. The description is insufficient for an agent to invoke the tool correctly without additional assumption.

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 coverage is 0%, and the description does not explain the meaning of the 'out' parameter (with default 'downloads') despite it being optional. It only reuses the parameter name 'candidate_id' in a description that says 'numeric candidate id', but the schema type is string, which is contradictory and unhelpful. The description adds no information about the 'out' parameter or the format expected for candidate_id.

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 action ('download'), the resource ('persisted allowed candidate'), and the identifier ('numeric candidate id'), and briefly mentions 'quarantine and provenance' which hints at additional output contents, distinguishing it from sibling search/analysis tools. However, it does not differentiate from the sibling 'get_*' tools explicitly, as they may also retrieve candidate-related data, but the verb 'download' suggests file retrieval.

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?

No guidance is provided on when to use this tool versus siblings like 'analyze_artifact' or 'get_report'. The description implies use when a persisted allowed candidate needs to be downloaded, but there are no explicit alternatives or exclusions. This is minimal guidance without context.

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