access_management.get_unused_columns_bulk

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

Annotations already indicate read-only and non-destructive behavior. The description adds valuable behavioral detail: it always returns a dict with 'results' and 'errors', returns a flat list across models, and normalizes a single string input. This goes beyond the structured annotation coverage.

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?

The description is well-structured: it opens with the core action, then details the return contract in a readable list. It is informative without being bloated, though the trailing ellipsis suggests some content may be omitted and the opening sentence overlaps slightly with the return explanation.

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?

Despite lacking an output schema, the description provides enough return structure for an agent to consume the result. It explains the combined across-models behavior and error grouping. It relies on knowledge of get_datamodel_columns row shape, which is reasonable given the sibling tool exists.

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?

The input schema already provides 100% parameter coverage, including accepted reference types and tolerant string normalization. The description does not materially add parameter-level semantics beyond restating 'one or more', so the baseline of 3 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?

The description clearly states the verb ('Run unused-column analysis') and the resource ('one or more data models'), and explicitly differentiates this as a bulk operation from the single-model sibling access_management_get_datamodel_columns. The output semantics are also described, making the tool's purpose unambiguous.

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 makes it clear this tool is for analyzing multiple data models at once and returns combined results, which implies when to choose it over single-model tools. However, it does not explicitly name alternatives or state conditions for when not to use it, so it falls short of the highest bar.

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