skill

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

Annotations indicate readOnlyHint=false, destructiveHint=false, etc. The description adds context: writes go to `skill_substrate` namespace, schema-validated at write time, and details each action's effects. It also explains the 'on_conflict' behavior. Some behavioral aspects (e.g., rate limits, concurrency) are not mentioned, but the description goes beyond 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 structured well: brief purpose, concept explanation, action list, examples, and args. It is front-loaded with the core role. While somewhat lengthy, every section adds value given the tool's complexity (multiple actions, 14 parameters). Could be slightly trimmed without losing clarity.

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?

Given the tool's complexity and the presence of an output schema, the description covers the key aspects: actions, parameter constraints, validation rules, and examples. It does not explicitly mention error handling or edge cases, but the examples and schema provide enough context for typical use.

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 has 14 parameters with 0% description coverage, but the description's 'Args:' section thoroughly documents each parameter, including constraints like 'dot-separated segments', '50–5000 chars', and '1–10 lowercase_underscore identifiers'. This adds essential meaning that the schema alone lacks.

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 tool is a 'Substrate-native agent skill catalog' and lists five actions (define, surface, outcome, get, list). It distinguishes this tool from the sibling 'procedure' by explicitly noting they are different and directing users to use `procedure` for loose how-to memories. The verb 'manage' is implied through the actions.

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 explicitly contrasts with 'procedure' and provides examples for each action, giving clear context on when to use each action. However, it does not provide explicit guidance on when not to use this tool in favor of other siblings (e.g., memory, recall), leaving some ambiguity.

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