catalog_run_adhoc_analysis

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

The description clearly discloses the asynchronous behavior: the job runs asynchronously, may take time, and requires polling with the returned id. It also describes what the job produces (data dictionary, column statistics, quality metrics) and the effect of the NLP parameters on asset metadata. With no annotations provided, this is solid behavioral transparency.

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 purpose in the first sentenceholaWhat is the function of the first paragraph? It explains the job result and async behavior, and second paragraph explains NLP params. Two concise paragraphs, each earning their place—no fluff. Slightly verbose in the middle with the bracket list, but acceptable.

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 description explains the job lifecycle (submit, poll), references related tools, and clarifies the side effects of NLP parameters. The schema already documents parameters fully, and the output is a job id which is implicitly referenced. Complexity is moderate (async, multiple boolean params), and the description covers it well, though it could mention expected job duration or error handling.

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 coverage is around 88% (7 of 8 params described in schema; resource_uri has a detailed example, the three booleans have detailed descriptions, name/description/provider are straightforward). The description adds crucial semantics for the three NLP booleans: they are enabled by default and drive informationPrivacy, nlpTags, etc., and explains when to disable them. This adds meaning beyond what the schema's terse descriptions ('default True') provide.

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: submitting an ad-hoc profiling job for a catalog table, with a specific verb ('Submit') and resource ('table in the catalog'). It distinguishes itself from sibling `catalog_download_table_profile` by noting the job computes what that tool returns, and from `catalog_get_adhoc_analysis` by mentioning the job id polling for completion.

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 explicitly states when to use the tool: to submit an ad-hoc profiling job, and how it fits with siblings (`catalog_download_table_profile` returns what this job computes; `catalog_get_adhoc_analysis` is polled with the job id). It also gives guidance on when to disable NLP parameters (plain profile only). It doesn't explicitly say when NOT to use it, but the context is clear enough.

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