delete_calculated_field

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

Goes well beyond destructiveHint=true by naming the concrete failure mode (references in visuals and other calculated fields break) and disclosing that a backup is automatically created. These are operationally important facts an agent cannot derive from annotations or schema.

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-loads the one-line purpose, then the destructive warning, then the mitigation tool, then the backup reassurance. Every sentence earns its place with 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?

With a destructive annotation, full schema coverage, and an output schema present, the description supplies exactly the missing pieces: blast radius, a verification tool, and backup behavior. Nothing needed for correct invocation is absent.

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 100% and both parameters (name, analysis_id) are documented in the schema, so the description adds no parameter-level detail. Baseline 3 applies when structured fields already do the work.

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 (delete) and resource (calculated field) scoped to a QuickSight analysis, distinguishing it cleanly from its siblings add_calculated_field, update_calculated_field, and list_calculated_fields.

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?

Explicitly tells the agent to run get_columns_used first to assess impact, which is actionable prerequisite guidance naming a sibling tool. It stops short of stating when deletion should be avoided altogether versus using update_calculated_field instead.

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