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

Annotations already establish idempotent=true, destructive=true, openWorld=true and readOnly=false; the description reinforces and explains these by disclosing content-addressing via SHA-256, free identical re-uploads (matching the idempotent hint), and the byte-dedup behavior that makes the larger body possible. It also documents the auth mechanism (X-Agent-Id/X-Signature/X-Timestamp or owner session), which the annotations do not cover. It stops short of describing what a successful publish returns or any failure modes.

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 core requirement is front-loaded, but the block is a single dense paragraph leaning on heavy capitalization (NATIVE, LARGER, REQUIRED, PAYLOAD-ONLY, FULL, AUTH) that is harder to parse than plain structure. The inline list of seven full runtime hashes is bulky, though arguably necessary.

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?

For a 13-parameter mutation tool with no output schema, the description covers the submission shapes, the mandatory runtime dependency, auth, dedup semantics, and the size limit. The main gap is the return value (presumably the content-addressed hash) and any error conditions, though the SHA-256 framing implies the return.

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 100%, so the baseline is 3, but the description adds real value beyond field-level docs: it explains the required runtime hash in deps, and the sequencing/mutual-exclusivity between entry_html and files+entry. It also enumerates valid runtime hashes inline, which the schema only refers to indirectly.

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?

Specific verb ('Publish') plus the exact resource ('xmbl-NATIVE miniapp') and its defining constraint (built on the shared xmbl runtime). It explicitly contrasts itself with plain apps (512kb body vs 256kb), which routes the agent away from publish_app. An agent can distinguish this from siblings without opening the schema.

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 clearly states when to use each of two submission shapes (PAYLOAD-ONLY with entry_html vs FULL with files+entry) and the mutual exclusion between them. It also states the hard prerequisite that deps MUST include an accepted runtime hash. What it lacks is explicit cross-referencing to the sibling publish_app/compose_apps for the non-native case.

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