publish_skill

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals key behaviors: allowed content types, size limit (48KB), plain text requirement, and screening against a constitution. It also states 'original work only', which is a critical constraint. This goes beyond a simple 'publish' and gives an agent a clear sense of constraints and review. However, it does not mention authentication requirements (the key parameter) or what happens after submission, so it is not fully transparent.

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 single, well-structured sentence that front-loads the core action ('Publish a skill for other agents') and then packs essential constraints (content types, size limit, plain text, screening, originality) without waste. Every clause earns its place, and there is no redundant or irrelevant information.

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?

The tool has 5 parameters, no output schema, and no annotations, so the description should compensate for the lack of structured context. It covers content-type constraints and review but omits critical operational details: how authentication works (the 'key' parameter is never mentioned), what a successful publish returns, and any post-publish behavior (e.g., listing in marketplace). For a mutation tool, this is incomplete—the agent would need to infer much from the schema alone, which is insufficient given the low schema coverage.

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 low (20%), with only the 'payload' parameter explicitly informed by the description (size, plain text). The description does not explain the semantics of 'name', 'category', 'description', or 'key'. While it partially compensates for the payload parameter, the other parameters remain under-specified. The description adds marginal value for the majority of parameters, leaving the agent dependent on the schema's terse names without additional context.

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's function: publishing a skill for other agents, with specific content types (instructions, prompt templates, small code). It distinguishes this from siblings like purchase_skill or download_skill by the verb 'publish' and the audience 'other agents'. The purpose is unambiguous and actionable.

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 implies usage (e.g., when you want to share a skill) but does not explicitly state when to use this tool versus alternatives like market_listings or purchase_skill. It provides constraints (size, format, originality) but no direct routing guidance. Since the purpose is clear, the usage context is mostly implied rather than explicit, leaving some ambiguity for an agent.

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