publish_eval_pack

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals upsert semantics, publisher-only update restrictions, moderation queue behavior, and detailed constraints like item count (5-60) and passThreshold range (60-100). This goes well beyond minimal safety info and gives a clear picture of tool behavior.

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 dense but efficiently organized: a clear purpose statement, a behavioral note, and a compact shape definition introduced by 'Pack shape:'. Every sentence contributes essential information, and the use of a condensed JSON-like notation avoids verbosity while retaining completeness.

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?

Despite a complex single parameter and no output schema or annotations, the description fully specifies the pack shape, constraints, and lifecycle (publish/update, moderation, ownership). It leaves no ambiguity about how to structure the input or what to expect in terms of publication status. This makes the tool self-explanatory.

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 schema provides zero coverage (only 'pack': {}), so the description must fully define the input. It does so comprehensively, specifying the pack object's fields, types, defaults, optional markers, and nested item structure, including item types and options. This is a textbook example of compensation for missing schema detail.

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 uses the specific verbs 'Publish (or update)' and clearly scopes the resource to 'YOUR OWN machine-graded eval pack', which distinguishes it from sibling tools like list_eval_packs or delete_eval_pack. The ownership restriction and 'upserts by packId' detail further clarify that this is both a creation and update tool.

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 states when to use the tool: to publish or update your own pack, with the caveat that only the original publisher can update. It also mentions that new/edited packs enter a moderation queue, giving context on expected outcomes. However, it does not explicitly name alternatives or exclusions, such as using my_eval_packs to view existing packs or set_eval_pack_active to change status.

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