generate_migration

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

With no annotations, the description carries full behavioral burden and fully delivers. It discloses that CREATE INDEX runs CONCURRENTLY, that non-ACCEPT verdicts are refused without an explicit override, that overrides are permanently stamped into the comment, and that the tool never executes migrations. These are non-obvious behaviors that significantly affect usage.

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?

Four sentences deliver purpose, formats, key behaviors, and usage constraints without redundancy. The structure is front-loaded with the primary action, then details, then an operational note. Every sentence earns its place; there is no filler.

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 description covers the essential aspects for a migration-generation tool: what it produces, allowed formats, the critical behavior around verification status, the override mechanism, and the safety guarantee of not executing migrations. Given an output schema exists, the description needn't detail return structure. It provides enough context for an agent to invoke the tool correctly and handle the result appropriately.

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%, so the description must compensate. It explicitly provides valid format values (sql, alembic, efcore) and explains the behavioral impact of allow_unverified (override stamped permanently). However, it does not explain the 'profile' parameter or explicitly tie 'verification_id' to the source record beyond the purpose statement. The description partially compensates but leaves some parameters underspecified.

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 opens with a specific verb and resource: 'Generate a migration FILE from a verify_index verification record.' It clearly distinguishes the tool from its siblings (like verify_index or propose_index) by focusing on migration generation. The mention of output formats (sql, alembic, efcore) further clarifies its purpose.

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 explicitly states when the tool is appropriate: it works from a verify_index verification record. It also gives a concrete exclusion criterion: 'Refuses non-ACCEPT verdicts unless allow_unverified=true.' The guidance to save the content rather than execute it ('pgverdict never executes migrations') provides clear operational instructions, effectively differentiating this tool from potential alternatives.

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