check_relationships

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

With no annotations, the description carries the transparency burden. It discloses the exact computation logic (count dimension members with no matching fact rows and fact keys with no dimension match) and explains why this causes blank visuals. It doesn't explicitly state that it is read-only, but 'Diagnose' strongly implies it, so this is not a major gap.

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 main purpose, and provides necessary context without any filler. Every sentence earns its place, making it highly concise and well-structured.

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?

Given the minimal schema, no output schema, and no annotations, the description explains the core diagnostic logic and when to run it. It lacks only a brief note about the return format or non-mutating nature, but the essential context is present.

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 description coverage is 0%, and the description does not mention 'sessionId' at all. While sessionId is likely a common session identifier, the description adds no semantic meaning beyond the name. The tool would benefit from at least stating that it operates on the model associated with the session.

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: diagnosing 'the visual is blank' issues by checking Fact->Dim relationships. It uses a specific verb ('Diagnose') and resource, and distinguishes itself from sibling tools like fix_broken_visuals by focusing on counts of orphaned members.

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?

Provides an explicit trigger condition: 'Run this whenever a visual is empty but the model looks fine.' This gives clear guidance on when to use the tool. It doesn't mention alternatives or exclusions, but the context is straightforward enough for a 4.

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