Lifecycle Classify Change

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

Annotations already mark the tool as read-only; the description adds deterministic behavior and the exact verdict structure. It also explains the classification logic and the role of Form/Fit/Function attributes, which goes beyond the structured annotations. No contradiction with annotations.

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-organized: decision logic first, outcome rules second, then parameter details, then return shape. The parenthetical '#141 C2' is minor noise, but otherwise every sentence adds useful information without redundancy.

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 read-only classifier with no output schema, the description covers all parameters, decision outcomes, and lists the returned verdict fields. The main gap is that 'noop' is mentioned as a possible disposition but not explained, and some verdict fields like 'f3' and 'categories' are listed without definitions.

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?

With 0% schema description coverage, the description carries the full parameter documentation burden. It explains that before/after are attribute objects representing interface-defining and internal attributes, and fully describes extra_f3 as a map from attribute names to form/fit/function legs. Slightly more detail on the internal shape of before/after objects would make it perfect.

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 states a specific deterministic predicate and the decision it produces: 'decide rename-vs-revise'. It clearly defines the input resource (before/after attributes) and the two meaningful outcomes, which distinguishes it from lifecycle_transition and lifecycle_apply_change.

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 intended use is evident: classify whether a proposed attribute change breaks interchangeability. It explicitly explains when 'new_part_number' vs 'revise' is the correct outcome, giving clear context for when to call it, though it does not name alternative tools or exclusion conditions.

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