save_draft

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

Annotations only declare readOnly=false, destructive=false, openWorld=false. The description goes well beyond that: it discloses rejection rules (Valve store rules, 8+ consecutive words copied from a reference game), rubric scoring, and the shape of the response (rubric findings plus questions). This is exactly the behavioral context 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?

Front-loaded with the core action and the non-mutation constraint, then validation behavior, then the strategy values, then the handoff. The strategy enumeration and trailing ellipsis make it slightly run-on, but every sentence carries information.

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?

An output schema exists, so return values need not be explained, yet the description still summarizes them (rubric findings plus questions). The validation rules and the set_field handoff make the workflow complete; the only real gap is the undocumented meaning of path/field/value.

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 0% across 5 parameters, so the description must compensate. It enumerates accepted strategy values (fantasy, mechanic, situation_humor, market_common, market_contrast, outline, text, revision) which is genuinely useful, but path, field, value, and notes remain undocumented in both schema and description.

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 ('Store a text YOU wrote as a draft') and immediately scopes it against the sibling that applies drafts ('it does not change steamworks.yaml', 'The user picks a draft with set_field(...)'). An agent can distinguish save_draft from set_field without opening either 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?

Names the follow-up alternative (set_field with from_draft=<id>) and the condition that selects it, and clarifies that this tool only stages text rather than applying it. It stops short of stating explicit exclusions (e.g. when to use set_field directly instead of drafting), but the workflow context is clear.

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