report_instances_download_data

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

With no annotations, the description carries full burden. It discloses side effects (saves to a TSV file, temp directory if no output_path), return statuses (success, no_data, error), and output details (file_size_mb, segment_count, row_count). It doesn't mention permissions, file overwrite behavior, or rate limits, which is a minor gap.

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 well-structured with a title, explanation, Args, and Returns sections. It's front-loaded with the core purpose, but the Returns section is somewhat verbose with inline descriptions. Still, every sentence earns its place.

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?

The output schema is embedded in the Returns section, covering status, file_path, file_size_mb, segment_count, row_count, and message. The description is self-sufficient for a 2-parameter tool, with no annotations needed. It lacks only background on access requirements and potential large-file handling, but overall it's quite complete.

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 does the heavy lifting. It provides meaningful explanations for both instance_id (analytics report instance ID) and output_path (optional, defaults to temp directory), adding clarity beyond the bare schema.

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 downloads analytics report data to a TSV file, with the specific verb 'download' and resource 'analytics report data'. It distinguishes itself from siblings by emphasizing it fetches all segments and saves to a file, unlike report_instances_get (metadata) or report_segments_get (individual segment).

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 clearly implies usage for downloading all report data for later analysis, and mentions the file can be analyzed using other tools. However, it doesn't explicitly contrast with alternatives like list_segments or get, nor state when not to use it, making it clear but without exclusions.

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