set_feature_code

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Create or update' usefully reveals upsert semantics (the tool won't fail if the feature already exists), but nothing is said about validation of AFDKO syntax, whether changes are applied immediately or reversibly, what happens on malformed code, or what the response contains. For a mutating tool with zero annotation coverage, this is a significant gap.

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 a tight docstring: one purpose sentence followed by three parameter lines, with the purpose front-loaded. Every sentence adds information and there is no filler. It's slightly mechanical in format but appropriately sized for a three-parameter tool.

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?

All three parameters are explained, so basic invocation is fully covered even with a bare schema. However, there is no output schema, no annotations, and the description omits behavioral context: what the tool returns, how errors in AFDKO syntax surface, and how this fits the broader feature/kerning workflow among 54 siblings. Adequate for a first call, but with clear gaps for a mutation tool.

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%, so the description must compensate — and it does. It supplies concrete feature tag examples ('liga', 'kern', 'ss01'), clarifies that code is in AFDKO syntax, and explains the meaning of active ('whether the feature is enabled'). This adds genuine meaning beyond the bare schema titles (Code, Active, Feature Name). It loses a point because the default value for active is duplicated from the schema and no format constraints for code are given.

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 opens with 'Create or update an OpenType feature,' which pairs a specific verb (create/update) with a concrete resource (OpenType feature). This is clear about what the tool does and implies write/upsert semantics that distinguish it from read siblings like get_features. However, it doesn't explicitly name or contrast with overlapping siblings such as auto_kern, which also manipulates feature-related data, so it stops just short of full differentiation.

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?

There is no guidance on when to invoke this tool versus alternatives. No mention that get_features should be used to read current feature code, or how this relates to auto_kern-generated features. An agent is left to infer the tool's role from its name and the sibling list, with no explicit conditions or exclusions.

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