export_data_dictionary

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

With no annotations, the description carries full behavioral disclosure. It explicitly states 'Rendered from the TOM tree only; no queries are run,' which reveals important performance and safety traits. It also mentions a coverage score feature and the content included. However, it does not disclose whether any write operations occur, return value structure, or error conditions, leaving some behavioral gaps.

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 a single long sentence containing multiple clauses, parentheses, and a semicolon. It packs in a lot of detail but is not ideally front-loaded; the most critical information (export of data dictionary, formats) comes first, but the coverage score explanation and TOM-tree note feel appended. It is moderately concise but could be broken into clearer sentences or bullets.

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 covers the main functionality, content, and a key behavioral trait (no queries run). However, with no output schema, it does not specify what the tool returns (e.g., a Markdown string, a file, a JSON object). It also leaves undefined terms like 'visible objects' and does not mention error handling or prerequisites. For a moderately complex export tool, it is adequate but has notable 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 50%: format has a description ('md | html'), but sessionId has none. The description does not explain sessionId's role (presumably identifying the model), nor does it add any detail about format beyond what the schema provides. The phrase 'the model' implies but does not explicitly connect to sessionId. Thus, the description does not compensate for the missing sessionId semantics.

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 a specific action ('Export the model's data dictionary'), identifies the resource (tables, columns, measures with descriptions/types/format strings/DAX, plus relationships), and specifies output formats (Markdown or HTML). It distinguishes this tool from siblings by focusing on the data dictionary plus a unique coverage score, which is not mentioned in sibling tools like document_report or export_tmdl.

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?

No guidance is provided on when to use this tool versus alternatives. There is no mention of scenarios where this export is preferred over document_report or get_model_summary, and no exclusions or prerequisites are stated. The only hint is that it uses the TOM tree and runs no queries, but this is not framed as a selection criterion.

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