Generate sqlc schema

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), but the description adds substantial context beyond them: the exact DDL emission order, the guarantee that the file replays cleanly against an empty database, that it runs in-process without MCPG_ALLOW_SHELL, and that the result is a single string. Only the return schema structure isn't restated, which is fine given the output schema exists.

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?

Front-loaded with the verb and output artifact, followed by ordered behavioral detail; nearly every sentence earns its place. The closing identifier-policy sentence with the docs reference is the one slightly heavy tail.

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 generator with an output schema and read-only annotations, the description covers output format, ordering, determinism, and the unsupported-identifier caveat well. The one real gap is the unexplained required 'schema' argument, which is more a schema/param issue than a behavioral one.

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 coverage is 50%: the 'database' parameter is documented in the schema but the required 'schema' parameter has no schema description and the description never explains it either. The long identifier-policy discussion concerns table/column naming, not the meaning of the 'schema' argument, so the description does not compensate for the coverage gap.

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?

States a specific verb and resource ('Read a PostgreSQL schema and emit a sqlc-friendly schema.sql') and names the exact output artifact. The sqlc target implicitly distinguishes it from sibling generators (prisma, drizzle, diesel, etc.) without ambiguity.

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?

Gives an explicit when-not rule with named alternatives: delimited names (hyphens, spaces, mixed-case-only) aren't supported, so use export_table or dump_database instead. Lacks a positive 'use this when you want sqlc output for a plain-identifier schema' statement, but the context is clear.

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