update_statistics

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

With no annotations provided, the description fully carries the burden. It clearly indicates the operation is an update (destructive in the sense of modifying statistics), explains the fullscan and sample_percent behavior, and states the supported environment. No contradictions.

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 well-structured: a summary line, a constraint note, then a clear parameter list. Every sentence adds value—no fluff or repetition. It is appropriately sized for the complexity (6 parameters).

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 complexity (6 params, 4 required) and the presence of an output schema, the description covers the core aspects. It explains the SQL command, parameters, and constraints. It might lack details on edge cases or error scenarios, but overall it is nearly complete.

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%, but the description compensates by explaining each parameter: workspace, item, qualified_table, stat_name, fullscan default and behavior, sample_percent with range and interaction. This adds significant meaning beyond the schema's bare titles.

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 updates an existing statistic via UPDATE STATISTICS, distinguishing it from siblings like create_statistics or delete_statistics. It also specifies the constraint of only being supported on Data Warehouses, not SQL Analytics Endpoints.

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 explicitly says 'Update an existing statistic' and notes the Data Warehouse requirement. It explains the difference between fullscan and sample_percent. It lacks an explicit 'when not to use' or references to alternatives, but the sibling context provides some implicit guidance.

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