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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world write, so the safety profile is covered. The description usefully adds that the draft lands in the person's Studio and that they can edit and publish it. It says nothing about whether repeated calls create duplicate drafts, what happens if both or neither payload parameter is sent, or what the call returns.

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?

Two sentences, no filler. The core action and destination come first, followed by the validation prerequisite and payload guidance in priority order.

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 three-parameter, all-optional, nested-payload write tool with no output schema, the description covers where the artifact goes and what the person does with it. It leaves the edge cases an agent would most want spelled out, namely behavior when both template and templateText are supplied or omitted, and confirmation of what a successful save looks like.

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 would be 3, but the description adds real meaning: templateText and template are alternatives (send one or the other), and model should be the caller's own model name so the person can tell drafts apart. The rationale for passing model is not present in the schema text.

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?

States a specific verb and resource: saves a game the agent wrote (or pulled from invent_status) as a draft in the person's Studio. The 'draft' framing implicitly separates it from publish_invented_game, but that sibling is never named, so the differentiation is left for the agent to infer.

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?

Gives a concrete prerequisite ('Check it first with check_invented_game') and tells the caller which of two payload parameters to send. It does not say when to prefer this over publish_invented_game or where draft creation fits relative to invent_game, so no explicit exclusions are offered.

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