catalog_download_table_profile

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

The description discloses the exact behavior: it returns a CSV of column metadata and profile, or if not profiled, a recommendation for adhoc analysis. This aligns with the annotations (`readOnlyHint: true`, `destructiveHint: false`, `idempotentHint: true`) and adds detail about the conditional output, which is transparent about side effects (none).

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 succinct, with no redundant information. It is well-structured in three sentences, covering purpose, fallback behavior, and parameter usage. It avoids verbosity while providing necessary context.

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 existence of an output schema (not shown), the description adequately covers the main functionality and edge case (unprofiled table). It explains the two possible outputs and the parameter resolution logic, which is sufficient for most use cases.

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?

The description clarifies the relationship between `instance_id` and `resource_uri`, stating they are alternatives and that `instance_id` takes precedence. This adds meaning beyond the schema descriptions, which already cover the basic purpose of each parameter.

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 function: 'Download a catalog table's data dictionary and profile as CSV.' It explicitly distinguishes it from related tools by describing the fallback behavior when a profile is not yet available, recommending `catalog_run_adhoc_analysis`.

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 explains when to use this tool versus an alternative: when the table is not profiled, it returns a recommendation to run `catalog_run_adhoc_analysis`. It also clarifies how to identify the table (via `instance_id` or `resource_uri`), giving precedence rules. However, it does not explicitly state general scenarios for choosing this over other catalog-related tools.

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