delete_statistics

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

With no annotations, the description carries full burden. It prominently warns 'This is a destructive, irreversible operation' and adds platform constraints (read-only SQL Analytics Endpoints) and the rejection case. This discloses the most important behavioral traits. It does not cover permissions, error behavior, or dependency conflicts, but for a destructive drop operation the core warning is present.

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 compact and well-organized: a one-line purpose, a two-line caution/constraint block, and a clean Args list. No filler; every sentence adds operational information. The destructive warning is front-loaded before the args.

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 four required parameters, zero schema descriptions, no annotations, and an output schema present, this description covers what the tool does, where it works, what is rejected, and what each argument means. The omission of return-value details is acceptable because an output schema exists. The warning and scope fully equip an agent to invoke it correctly.

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%, so the description must compensate and does. Each of the four required parameters gets a meaningful explanation: workspace (name/GUID), item (warehouse name/GUID, with SQL Analytics Endpoints rejected), qualified_table (with an example), and stat_name. This adds real semantic value the schema lacks.

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 opens with 'Drop a statistic via DROP STATISTICS', naming a specific verb ('Drop') and resource ('a statistic'), and equates it to the SQL command. This distinguishes it clearly from sibling tools like create_statistics, update_statistics, and list/show_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?

It explicitly states the tool is 'Only supported on Data Warehouses (SQL Analytics Endpoints are read-only)' and later repeats that SQL Analytics Endpoints are rejected for the 'item' parameter. This gives clear context and a hard exclusion, though it does not explicitly name alternatives or say 'use this when you need to permanently remove a statistic' beyond the obvious purpose.

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