Catalog Download Table Profile

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

Annotations already mark this as read-only and idempotent, and the description adds substantial behavioral context beyond that: it returns a recommendation to run catalog_run_adhoc_analysis instead of an empty profile when profiling is missing, resolves resource_uri via resourceId like catalog_find_instance, and documents that instance_id takes precedence when both are supplied.

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 front-loaded with the core action and output in the first sentence, then adds fallback behavior and parameter-selection details in short, purposeful paragraphs. Every sentence contributes distinct information without repetition.

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 read-only download tool with rich annotations, full schema coverage, an output schema, and an important edge case, the description covers the result format, unprofiled-table behavior, parameter precedence, and relevant sibling workflow. No critical usage information is missing.

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 schema already describes all three parameters, but the description adds critical non-redundant semantics: the caller must provide either instance_id or resource_uri, instance_id takes precedence if both are given, and resource_uri supports a search → profile → download workflow without handling an instance id. This materially improves parameter understanding beyond the 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 opens with a specific verb and resource: 'Download a catalog table's data dictionary and profile as CSV.' It also distinguishes the tool from siblings like catalog_run_adhoc_analysis by describing the unprofiled-table fallback, so an agent can clearly identify what this tool does.

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 states when the tool is appropriate (downloading metadata/profile) and names the alternative catalog_run_adhoc_analysis for the unprofiled-table case. It also provides clear guidance on choosing instance_id vs resource_uri, including the workflow benefit of resource_uri. It does not exhaustively compare to all catalog siblings, but the guidance is strong.

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