stamp_vertipaq_stats

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

With no annotations provided, the description carries the full burden. It clearly discloses that the tool performs both a read (from live DMVs) and a write (annotations to the model definition). It specifies the exact annotations written and the persistence purpose. It lacks details on whether it overwrites existing annotations or potential performance impacts, but the core behavior is 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 two sentences, front-loaded with the main action and purpose. The second sentence clarifies the read/write behavior. There is no redundant filler, 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?

For a tool with no output schema and no annotations, the description provides the essential context: what it does, why, and the effect on the model definition. It does not mention return values or elaborate on side effects, but the core operation is well-covered. It is reasonably complete for an agent to select and invoke the tool properly.

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 has one required parameter, sessionId, with a 0% description coverage. The description does not mention or explain sessionId at all. While the parameter is likely a common session identifier, the description adds no meaning beyond the name, and given the low coverage, it should have been explained or contextualized.

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 function: it reads storage DMVs and writes VertiPaq stats as specific Vertipaq_* annotations per column. It names the exact annotations (Vertipaq_TotalSize, Vertipaq_DictionarySize, Vertipaq_Cardinality), distinguishing it from generic annotation tools like set_annotation and from read-only stats tools like column_statistics.

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 gives a clear use case: persist stats for offline review in the model definition. It also notes the tool reads from the live engine and writes annotations, implying that it should be used when a persistent record of VertiPaq settings is needed. However, it does not explicitly mention alternatives or when not to use it, so it misses a perfect score.

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