recipe_publish

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

No annotations and no output schema, so the description carries the full burden. It does disclose the meaningful behavioral fact that the recipe leaves the user's private space and enters a community moderation queue for human review, which is real value. However, the truncated trailing clause presumably covered further behavior (reversibility, what happens on approval/rejection, required permissions) that is now missing.

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?

What is present is a single front-loaded sentence with no filler, which is the right shape. The sentence is cut off mid-word however, so the definition as delivered is structurally incomplete rather than concise.

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?

This is a mutating, externally-visible action with no annotations and no output schema to fall back on, so the description needs to carry the full behavioral story. It names the destination and reviewer but omits irreversibility, approval flow, and preconditions, and the text is truncated before those details could appear.

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 tool takes zero parameters, so there is no parameter surface for the description to document or for the schema to obscure. Baseline 4 applies.

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 visible text states a specific verb and resource - submitting a saved recipe/skill - and names the destination, the community moderation queue for Dario's review. That distinguishes it from siblings like recipe_save, recipe_run, and recipe_install. The sentence is truncated mid-clause ('this does N...'), so the scope is clear but incomplete.

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 explicit statement of when to publish versus when to use recipe_save, recipe_export, or recipe_install, nor any prerequisites such as needing the recipe saved first. The submission-to-review framing implies intent but leaves the agent to infer the trigger conditions.

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