Generate Ent schemas

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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds substantive behavior: composite FKs are a documented v1 gap, the identifier-policy constraint on schema/table/column names, and the fact that output is a JSON {filename: source} map the agent must write itself. That is real context beyond the annotations, though it omits anything about volume/limits on large schemas.

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 core action and output shape, then constraints and the documented gap. Every sentence carries information, though the single dense paragraph mixes purpose, output format, limitations, identifier policy, and a doc pointer, which slightly hurts scannability.

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?

Given an output schema exists, return values need not be explained, yet the description still notes the JSON map shape. It covers the v1 composite-FK gap, identifier restrictions, fallback tools, and a docs reference. The only residual gap is that the required schema parameter itself is never explicitly defined.

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 50%: the schema param is undocumented in the schema and only implicitly explained by 'read a PostgreSQL schema', while the database param's meaning is already fully covered in the input schema (secondary read-only database, use list_databases). The description does not add format or identifier-rules detail tied specifically to the schema parameter beyond the global identifier policy note.

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 precise verb (read a PostgreSQL schema) and the exact artifact produced (Ent Go schema struct files, one .go file per table), including what constructs get emitted (field.X, edge.To, field.Enum().Values()). This cleanly distinguishes it from the sibling ORM generators like generate_prisma_schema and generate_drizzle_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?

Gives an explicit exclusion with named alternatives: delimited identifiers (hyphens, spaces, mixed-case-only) are unsupported, and the agent should use SQL tools (export_table, dump_database) for those objects. It does not, however, say when to prefer Ent over the sibling Prisma/Drizzle/SQLAlchemy generators, so the guidance is clear but not exhaustive.

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