pbi_add_table_from_source

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

Annotations only provide hints (readOnlyHint=false, destructiveHint=false, etc.), but the description goes far beyond them. It discloses critical behavior: the query is written and validated, but the first refresh requires manual credential entry in Desktop, the table exists without data until then, and the server cannot verify the connection. It also states that TMDL requires the project to be closed in Desktop. This is exceptional 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 well-structured with a lead sentence, bullet-like source-specific instructions, and a bolded 'truth about credentials' note. Every sentence adds value; there is no fluff or repetition. The use of markdown-style highlighting makes it easy to scan despite its length.

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 complex tool with 14 parameters and no schema-level descriptions, this description is remarkably complete. It covers the main use cases, the nuance of credentials and refreshes, and the prerequisite of a closed Desktop project. Given an output schema exists, the lack of return-value details is acceptable. The description leaves no major operational gaps.

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 0%, so the description carries the full burden. It explains the meaning and constraints for core parameters: source, server, database, schema, source_table, native_query, url, json_path, and columns. It clarifies json_path traversal, type culture nuances, and why columns must be explicit. However, some parameters (table_name, dry_run, overwrite, request_id, description) are not described, though their names are self-explanatory.

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: 'Crea una tabla apuntando a una BASE DE DATOS o API externa.' This clearly distinguishes it from sibling `pbi_add_table_from_file` by indicating the source type (external DB/API vs file). The supported source types are enumerated, making the tool's scope unambiguous.

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 gives concrete guidance for each source type (sqlserver, postgresql, odata, web_json) and explains required parameters (e.g., columns mandatory). It also notes that native_query is only for sqlserver and that the project must be closed in Desktop. However, it does not explicitly contrast with pbi_add_table_from_file or specify when to choose this tool over alternatives beyond the source type.

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