Draft an offer

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

Annotations already say readOnlyHint=false with openWorldHint=false; the description goes further by disclosing that the draft is 'saved on this computer' and that 'nothing is sent and nothing reaches Trood,' which is exactly the side-effect information an agent needs before invoking a write. It does not say whether repeated calls overwrite an existing draft or create a new one.

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?

Four sentences, front-loaded with what gets drafted and what goes into it, then the safety statement. No filler, though the safety clause and the 'let them change it' instruction overlap slightly in intent.

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?

Covers inputs, provenance constraints, persistence location, and the no-network guarantee for a 6-parameter mutation with no output schema. The remaining gap is what the call returns (a draft id or handle) so the agent knows how to reference the draft later, but this is minor given the otherwise thorough disclosure.

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 semantics: facts must be 'recorded ones only' and each is shown with its source, and options come 'from one industry in get_catalog' with an optional agent-supplied price. That links parameters to sibling tools in a way the schema text does not.

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 artifact: 'Drafts the brief the company's management will read,' then enumerates its constituent parts (headline, heard, facts, options, price). The closing line 'before they publish it' implicitly separates this from publish_offer, so an agent can distinguish the two without opening a 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?

Clear context for use: show the brief to the person and let them change it before publishing, which positions this ahead of publish_offer in the workflow. It also constrains inputs ('recorded ones only', 'options from get_catalog'). It stops short of an explicit when-not-to-use statement or naming publish_offer directly.

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