impact_analysis

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

With no annotations provided, the description carries the full burden and it does well: it discloses the read-only nature and explains the transitive traversal over DAX dependants. It also clearly states how the optional reportSource changes behavior to include report visuals. It doesn't mention error cases or performance, but the key safety aspect is thoroughly covered.

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 two sentences, front-loaded with the memorable 'BLAST RADIUS' phrase, and every word earns its place. It packs a lot of detail without bloat.

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 no output schema, the description explains what the tool returns (dependants and optionally visuals) and why it's used. It could be slightly more explicit about the return format or edge cases, but the core purpose and scope are well covered.

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 schema already provides 100% coverage, so the baseline is 3. The description adds meaningful context: it clarifies that objectName can be a bare measure name or Table[Field], and it explains that reportSource expands the analysis to report visuals. This goes beyond simple schema descriptions.

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 uses the vivid 'BLAST RADIUS' metaphor to immediately convey a specific, bounded analysis: find all DAX and report references to one model object. It clearly states the resource (a measure name or Table[Field]) and explicitly positions itself as a 'pre-rename / pre-delete safety check', distinguishing it from generic dependency tools like analyze_dependencies.

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?

It explicitly says 'The pre-rename / pre-delete safety check', giving a clear scenario for when to use this tool. It also notes 'Read-only', which signals it's safe to call. However, it does not explicitly name alternative tools or say when NOT to use it, so it misses the highest bar.

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