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

Annotations only declare the basic safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds the things an agent actually cannot infer: that the template is persisted so others can reuse it, that validation checks re-run and can take up to a minute, and that a user-level permission setting silently changes the outcome to a draft. That latency and permission-gating disclosure is genuinely valuable context beyond the annotations.

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?

Three dense sentences with the action and side effects front-loaded, then the gating condition, then the numeric constraint — a sensible order. The parenthetical asides accumulate, and '(draft: true)' reads like a parameter reference that doesn't exist, costing a little clarity.

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 5-parameter mutation with a nested `template` object and no output schema, the description covers source of input, side effects, latency, permission-dependent outcome, and the numeric constraint on stakeOptions. What it omits is what the caller gets back (game id? draft id?) and what happens on a failed check, which an agent would want given the up-to-a-minute re-validation.

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 80%, so the baseline is 3, but the description adds real meaning beyond it: it names where `template` must come from (invent_game / invent_status / get_game_kit), clarifies that `templateId` substitutes for saving this one as a template, and documents the stakeOptions domain (0 or 10..1000, max 6, increasing order) that the schema leaves entirely undescribed. The '(draft: true)' phrasing is ambiguous since no `draft` property exists in a closed schema, which keeps this from a 5.

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 + resource ('Publishes an invented game') and immediately qualifies the two valid sources (a ready invent_status template or one written yourself via get_game_kit). It also names the concrete side effects — saving the template and putting the game live in the feed — which separates it cleanly from save_invented_draft and from the sibling publish_skill_game / publish_luck_board variants.

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 clear entry condition (template must come from invent_status or get_game_kit) and explains the fallback path when the user's 'Publish invented games without asking me' setting is off — the game becomes a draft published from Studio. It does not explicitly say 'use save_invented_draft instead if you only want a draft', so the alternative routing is implied rather than stated.

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