Write Query

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

With no annotations provided, the description carries the full behavioral disclosure responsibility. It identifies that commands are DDL/DML, which implies modification, but it never mentions that these commands can change or destroy data, what is returned (only that no ResultSet), or permissions/risks involved. The description does not explain the actual behavior of the command execution beyond the SQL, leaving the agent without safety expectations.

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 brief and to the point: it states the operation and directs session-db setup to a sibling. There is no filler. The grammar is slightly informal ('do not have' instead of 'do not return') but the sentence is easy to skim.

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?

The absence of an output schema and annotations means the description should carry the full weight of what the tool does. It covers that the tool has no ResultSet, but it omits the return/success format, the potential damage or side effects on data, and how db interacts with the session. The tool is probably simple, but for a write/DDL tool these details are necessary for safe and correct invocation.

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% – the schema already labels query as 'SQL to execute' and db as 'database'. The description adds the pointer to set_session_db for a default database, which provides additional context. But it does not clarify whether the db parameter overrides the session default, or how the optional db and session default interact.

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 the tool executes DDL/DML or other StarRocks commands that do not return a ResultSet, and points to set_session_db for a per-session default database. This clearly identifies the verb and resource range and implies a distinction from read_query, though the phrasing 'other StarRocks command' is a bit broad and does not explicitly name the read alternative.

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 explains that set_session_db should be used for setting a per-session default database, and implies this tool is for commands without a ResultSet. However, it does not explicitly state when to use this as opposed to read_query, nor does it give clear when-not-to-use criteria or exclusions. The usage context is only implicitly conveyed.

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