Выполнить изменяющий SQL-запрос

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

Annotations already mark the tool as destructive and non-read-only, so the description's job is to add behavioral context. It does abundantly: immediate execution without a transaction, no rollback possible, permission gating via environment variables requiring restart, DDL unsupported regardless of config, and full-table protection requiring explicit confirmation. This exceeds what the annotations convey.

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 information-dense, with the core function front-loaded first, followed by permission constraints, DDL exclusion, transactional behavior, and full-table guardrails. Every sentence earns its place and no content is redundant filler.

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 mutating SQL tool with no output schema, the description is complete: it covers supported statement types, permission requirements, environmental configuration, unsupported DDL, rollback impossibility, full-table confirmation, and the return value (affected-row count). An agent has what it needs to decide whether and how to invoke it safely.

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 100%, and the schema already explains sql, params substitution, and allow_full_table confirmation semantics. The description reinforces these points but does not add new parameter-level meaning; its extra value is mostly about execution behavior rather than parameter semantics.

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 states a specific verb and resource: it executes one mutating SQL query (INSERT, UPDATE, DELETE, or REPLACE) and returns the affected-row count. This clearly separates it from read-oriented siblings like query and explain, even without naming them.

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 strong when-to-use and when-not-to-use guidance: mutations require configuration flags and a server restart, DDL is never supported, and full-table UPDATE/DELETE need allow_full_table=true. It does not explicitly point to a sibling read tool for SELECT queries, but the 'server allows only reading' caveat makes the intended usage largely inferable.

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