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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false. The description adds genuinely new behavior: generation runs asynchronously in the background and results must be read later, which is essential for an agent to avoid expecting synchronous output. It omits rate limits, expected latency, and whether re-queuing duplicates work.

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?

One tight sentence that front-loads the async nature and the result-retrieval instruction. 'Some records' is a bit vague but nothing is padded.

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 exists, yet the description doesn't say what a successful call returns (job id? count?) or how failures surface — and the required baseId/table/field identifiers are unexplained. For an async mutation tool this leaves an agent guessing about the immediate response.

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% across five parameters, so the description must carry the load. It only gestures at two optional params ('some records' → records, 'never generated' → missingOnly) and says nothing about baseId, table, field formats, or the 5000-item cap on records.

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 ('Queue AI generation ... of an AI field') and signals scope modes (some records, missingOnly, whole column), which distinguishes it from sibling mutators like create_field or update_field. It stops short of explicitly naming those siblings as alternatives.

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 three operating modes (records list, missingOnly, whole column) imply when to pick each, but the description never states preconditions — e.g. that the field must already be an AI field, or how to discover AI services via list_ai_services. Usage is inferred rather than stated.

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