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

Beyond the annotations (destructive, non-idempotent, non-read-only), the description discloses the auth requirement (stack:write), the safety gate (confirm=true), non-obvious failure semantics (unknown names are returned unmatched and never create tools), and downstream consequences (immediate publication, no editorial review, public visibility tied to profile state). That is exactly the extra context the annotations cannot carry.

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?

Four short sentences, front-loaded with the verb and resource, then progressively revealing prerequisites, write semantics, and publication side effects. No filler and no restatement of the tool name.

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?

There is no output schema, and the description adequately covers the result of a preview (unmatched names returned), the write confirmation requirement, and publication consequences. It stops short of describing the shape of a successful sync result or the item cap, which are the only remaining gaps for a destructive bulk 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 coverage is only 33% and the nested item fields carry no descriptions, but the description compensates by explaining what items mean (names matched against existing tools, unmatched entries returned rather than created) and what confirm does (false = preview, true = write). The 200-item maxItems cap and the slug/source/version/role fields are still left to the schema.

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 first sentence names a specific verb pair (preview / atomically replace) and the exact resource (the token owner's aicoolies stack), so the operation is unambiguous. It does not compare itself against any sibling tool, but none of the listed siblings (get_tool, search_tools, upvote_tool, submit_run, etc.) perform a stack write, so no differentiation is really needed.

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?

It states the mode-selection rule explicitly (preview by default, confirm=true to write) and the required scope stack:write, which tells the agent when the tool is callable and when it will actually mutate. It does not name an alternative tool or state exclusion cases, which keeps it short of a 5.

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