seeany_download_assets

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

Annotations only mark the tool as non-read-only and non-destructive. The description adds real behavioral context: it writes output files into a local directory and returns their paths. It does not mention overwrite behavior or directory creation, but for a download operation the core side effect is disclosed.

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 sentence with no fluff: action, resource, destination, and return value are all front-loaded. Every word contributes to understanding.

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 simple two-parameter download tool, the description covers the main flow but leaves gaps like output_dir creation/overwrite behavior and the exact representation of returned file paths. It is adequate but not fully self-sufficient.

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 0%, so the description must carry the burden. It indirectly maps output_dir to 'local directory' and job_id to a 'completed SeeAny' job, adding some meaning, but it does not explain formats, whether output_dir is auto-created, or required job state in detail.

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 action (download), resource (completed SeeAny output images), destination (local directory), and return value (file paths). It is clearly distinct from siblings like upload_asset or get_generation, none of which download output images.

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?

The word 'completed' implies this should be used after a SeeAny generation has finished, which is a useful contextual cue next to wait_generation. However, it never explicitly says when to use this versus alternatives, and no exclusions are mentioned.

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