execute_select

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

With no annotations, the description carries the full behavioral burden and does so well: it enumerates what is rejected (DML/DDL, SELECT INTO, FOR UPDATE/SHARE row locks, multi-statement, dangerous functions) and states that execution happens inside a server-enforced read-only transaction. It also discloses that max_rows defaults to instance config and is bounded by a server hard cap, which is exactly the kind of constraint an agent needs to avoid failed or oversized calls.

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 text is front-loaded with the core purpose, then constraints, then usage, then the max_rows note — a logical progression with no filler. It is dense but every clause about rejection rules earns its place; the closing max_rows sentence is mildly redundant with the schema description.

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 mutation-free query tool with no annotations and no output schema, the description supplies the safety profile (read-only transaction, rejected statement types), the workflow position relative to siblings, and the row-limit behavior. An agent has everything needed to construct a valid call and anticipate rejection conditions.

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%, so the schema already documents sql, instance, and max_rows, giving a baseline of 3. The description largely restates those constraints (single SELECT/WITH, default row limit, server cap) without adding syntax, format, or error-handling detail beyond the schema; the instance parameter is not elaborated on at all.

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 (execute a read-only SELECT query) and immediately frames scope: '本服务器唯一允许的 SQL 入口' (the only allowed SQL entry point on this server). It also distinguishes itself from siblings by describing the workflow with list_tables/describe_table as the locating step, so an agent can tell it apart from the metadata tools without opening any schema.

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?

Usage is explicit: use it after locating a target via list_tables/describe_table for data exploration and statistics (counts, aggregation, sampling, top-N ordering). It also gives an operational alternative rule — prefer LIMIT or aggregation for large result sets to reduce transfer. Both when-to-use and the sibling workflow are stated, leaving little to inference.

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