export

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

Annotations already indicate read-only and non-destructive behavior, but the description adds valuable context beyond this: it specifies the scale limit ('up to 1M rows'), automatic saving to 'Downloads/Metabase folder', and support for multiple export formats. This enhances transparency about operational constraints and outcomes without contradicting annotations.

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 appropriately sized and front-loaded, with a single sentence that efficiently conveys the core functionality, scale, formats, and saving behavior without unnecessary details. Every element earns its place by adding value, such as the row limit and folder path, making it concise and well-structured.

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's complexity (7 parameters, no output schema) and rich annotations, the description is mostly complete: it covers purpose, scale, formats, and saving behavior. However, it lacks details on error handling, authentication needs, or rate limits, which could be useful for a tool handling large exports. With annotations covering safety, this is a minor gap.

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?

With 100% schema description coverage, the input schema fully documents all 7 parameters, including their purposes and constraints. The description adds minimal parameter semantics, only mentioning 'specified format (CSV, JSON, or XLSX)' and 'automatically saves to Downloads/Metabase folder', which aligns with the schema but doesn't provide significant additional meaning. This meets the baseline for high schema coverage.

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 with specific verbs ('export large SQL query results or saved cards') and resources ('Metabase export endpoints'), distinguishing it from siblings like 'execute' or 'retrieve' by focusing on data export rather than execution or retrieval. It specifies the scale ('up to 1M rows'), output formats, and automatic saving behavior, making the purpose unambiguous and differentiated.

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 description provides clear context for when to use this tool ('export large SQL query results or saved cards') and implies usage for bulk data export scenarios. However, it does not explicitly state when not to use it or name alternatives among siblings (e.g., 'execute' for running queries without export, 'retrieve' for fetching data without saving), leaving some guidance gaps.

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