find_unused_fields

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

With no annotations, the description carries the disclosure burden and does well: it warns the result is not guaranteed-safe-to-delete and enumerates the blind spots (DAX-only references, tooltips, drillthrough, Q&A) via the note field. It would be stronger if it stated read-only behavior or any performance/cost characteristics explicitly.

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?

Front-loads what the tool finds, then follows with prerequisite, then caveat — a sensible order with no filler. The sentence structure is somewhat dense with parentheticals, but every clause adds information.

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?

An output schema exists, so return values needn't be described, and the description still points at the `note` field for caveats. The main gap is the unexplained `instance` parameter for a tool requiring two inputs with zero schema documentation.

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 description coverage is 0%, so the description must compensate. It explains where pbix_path comes from, which is genuinely useful, but the required `instance` parameter is never mentioned, leaving half the required inputs undocumented anywhere.

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?

States a specific verb and resource with precise scope: visible columns and measures no visual on any report page uses. The parenthetical clarifies the mechanism (live model cross-referenced against offline report layout), which distinguishes it from sibling listing tools like list_columns or list_measures.

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?

Gives concrete prerequisites by naming where to obtain pbix_path (list_open_files's file_path, or find_pbix_files). It also frames the output as a lead for model cleanup rather than an authoritative deletion list, which guides interpretation. It does not, however, contrast it against neighboring diagnostics such as analyze_model_size or check_refresh_dependencies.

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