Catalog Run Adhoc Analysis

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

Annotations provide no meaningful hints (all false), so the description carries the burden of behavioral disclosure. It explicitly states the job runs asynchronously and may take a while, which is critical for an agent deciding whether to wait or poll. It also reveals that the three NLP parameters are enabled by default and drive semantic enrichment around informationPrivacy, nlpTerms, nlpTags, and mostImportantFields, including a performance tradeoff for disabling them. This goes well beyond the schema and 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 well-structured and front-loaded with the core action, followed by the profile contents, then the async workflow, then the NLP parameter guidance. Each sentence adds useful information and there is no filler. It is slightly longer than minimal, but every paragraph serves a distinct purpose.

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 tool with 8 parameters, an output schema, and asynchronous behavior, the description is complete: it explains what the job produces, how to retrieve the result, what the default NLP parameters do, and when to consider disabling them. The output schema covers return values, and the schema covers parameter syntax. Nothing needed for correct invocation or follow-up polling 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 input schema already documents all 8 parameters at 100% coverage, so the baseline is 3. The description adds meaningful semantics beyond the schema, especially for the NLP booleans: it explains they drive semantic enrichment and affect job duration, and it clearly names the asset fields they populate. It does not add detail for every parameter, but the schema handles those adequately.

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: 'Submit an ad-hoc analysis (profiling) job for a table in the catalog.' It then clarifies what the job produces (data dictionary, column statistics, data-quality metrics) and explicitly distinguishes it from sibling tools like catalog_download_table_profile and catalog_get_adhoc_analysis. An agent can tell exactly what this tool does and how it fits into the catalog workflow.

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 clearly explains the asynchronous workflow: submit the job, receive a job id, and poll catalog_get_adhoc_analysis until the profile is ready. It also names catalog_download_table_profile as the tool whose output this job computes, giving context for when a precomputed profile might be the alternative. It does not explicitly state when to use one over the other, but the polling instruction and sibling references provide strong practical guidance.

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