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

With no annotations, the description carries the full burden and does it well: it discloses auth requirements (Bearer token), exact cost (€0.002 per query), doubled pricing for fix=true, that the fix path calls a model and re-validates the result, and the critical safety fact that it never connects to a database. This is exactly the behavioral context an agent needs before invocation.

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?

Functionality is front-loaded, followed by cost/auth/safety, then a compact per-parameter glossary. Dense but every clause earns its place, and the semicolon-delimited parameter list keeps six params readable in one paragraph rather than padding the text.

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 six-parameter tool with an output schema and no annotations, the description covers purpose, cost, auth, safety, and all parameter meanings, so an agent can invoke it correctly. Minor gaps: the accepted dialect list is truncated ('tsql…') and no guidance on how fix behaves when the query already parses.

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% and all six parameters are typed merely as nullable strings, so the description must compensate — and it does, defining sql, dialect (with default 'generic'), to_dialect, schema as JSON {table: {column: type}}, pretty, and fix. It even resolves the schema's string typing for pretty/fix by declaring them booleans, though that mismatch with the schema could itself cause confusion.

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 enumerates concrete capabilities with specific verbs and resources: parse errors with line/column, dialect translation across named dialects, schema checking, pretty-printing, and optional LLM-based fixing. An agent can tell exactly what the tool does. It stops short of a single crisp verb+resource statement (the word 'SQL' appears only in parameter context) and does no sibling differentiation, so not a 5.

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 implied rather than stated: the agent can infer that to_dialect should be set when translating and fix=true when a corrected query is wanted. There is no explicit when-to-use/when-not framing and no named alternative (e.g., a plain SQL formatter or regex_test), though no close sibling exists in the list.

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