delete_feature

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

With no annotations present, the description carries the full burden and does so well: it discloses the refuse-on-dependents behavior and that dependent features are named, the with_children override, dry_run semantics (would_delete), the equation breakage and broken_equations reporting, the with_equations override with the caveat that global variables survive, and the implicit rebuild/remeasure side effect.

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 conditions in a logical order. Dense and slightly run-on in the middle clause ("names them, and what is built on those"), but essentially every sentence conveys a distinct behavioral fact.

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?

For a destructive, four-parameter tool with no annotations and no output schema, the description is nearly self-sufficient, even naming return keys (would_delete, broken_equations). Minor gaps remain around confirmation/permission expectations and the source from which the feature name must be obtained.

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 coverage is 0%, so the description must compensate for all four parameters, and it explains dry_run, with_children, and with_equations precisely in terms of observable effects. The required name parameter is only glossed as "a list_features name," leaving its format slightly implicit, but overall coverage is strong.

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?

Specific verb ("Delete") plus resource ("a feature"), and it even resolves the argument identity by pointing to list_features names. It also frames the operation as "the way to undo a step," which distinguishes it from sibling mutators like suppress_feature and delete_equation.

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 clear operational context (undo a step) and conditions under which behavior changes: refuses when children exist, with_children=True overrides that. However it never explicitly contrasts delete_feature against the obvious sibling alternative suppress_feature, so an agent must infer when deletion beats suppression.

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