model_health

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

With no annotations, the description must carry the transparency burden. It explicitly states 'Read-only' and explains the data source (storage DMVs via the model connection), which are key behavioral traits. It does not mention potential performance impacts of querying DMVs or permission requirements, but for a read-only report this is reasonably transparent.

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, information-dense sentence followed by 'Read-only.' It front-loads the purpose ('Model-health report'), specifies the data items (object counts, VertiPaq storage, size, cardinality), and ends with a clear use case. No unnecessary words or repetition.

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 tool's simplicity (one parameter, no output schema), the description covers what the report contains, its data source, and its intended use. It does not explicitly state prerequisites like an active model connection, but 'through the model connection' implies it. This is sufficient for an agent to understand when and how to invoke the tool.

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 sole parameter sessionId is not described in the schema or in the description, and schema description coverage is 0%. The description does not compensate by explaining what sessionId refers to, leaving the agent to infer its meaning from context and sibling tools. Since the parameter name is self-explanatory in this domain, a score of 2 is given rather than 1.

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 produces a model-health report covering object counts and VertiPaq per-column storage, with a specific purpose of surfacing large/high-cardinality columns for bloat analysis. It distinguishes itself from sibling tools like get_model_summary or column_statistics by emphasizing DMV-sourced storage metrics and the bloat-finding use case.

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 implies usage for diagnosing model bloat and unused high-cardinality columns, and notes it reads from storage DMVs through the model connection. It does not explicitly compare to alternatives or state when not to use it, but the context is clear enough for an agent to select it over similar read-only diagnostic tools.

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