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

Annotations declare destructiveHint=true, but the description adds substantial context beyond that: exactly what is lost (stored rows on retype, row data orphaned under the old key on rename), the org-wide blast radius ('a schema change lands for every flow and station'), the blueprint constraint, and the partial-failure model ('Per-operation failures are collected rather than aborting'). This is meaningful disclosure an agent could not infer from the annotations alone.

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, then layered with the scoping constraint, the safety rule and the failure model. Every sentence carries distinct, load-bearing information and none restates the title or schema.

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?

No output schema, but the description needn't explain return values; it instead covers the things that matter for a destructive mutation: scope, irreversibility, downstream dependents, and error behavior. Nothing an agent needs in order to call this safely is missing.

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 60%, so the schema already documents tableName, hubToken, removeFields and the reference fields. The description maps its language onto addFields/updateFields/removeFields and reinforces that rename/retype is destructive, but adds no syntax or format detail beyond the schema. A 3 baseline is appropriate.

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 ('Evolve an EXISTING custom data table's schema') and enumerates the three sub-operations (add, change, drop columns). It is clearly distinguishable from sibling flow_create_custom_table and flow_list_custom_tables, which it references by name.

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 explicit when-to-use ('EXISTING' table, identified by kebab-case name from list_custom_tables), when-not ('use sparingly' for rename/retype) and hard exclusions ('NEVER rename or reshape a table a selfPersisting blueprint reads/writes'). The alternative path (list_custom_tables) is named directly.

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