draft_tweet

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

With no annotations, the description carries full burden. It discloses the non-posting behavior and the API key prerequisite, which are key behavioral traits. However, it does not explain what happens to the draft (e.g., if it is saved, returned only, or if there are rate limits). Since it is a mute operation with no side effects mentioned, this is a moderate disclosure.

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 three concise sentences: purpose, non-posting clarification, and API key requirement. Every sentence adds value and is front-loaded. No unnecessary detail or repetition.

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 simple tool with 2 parameters and an output schema, this description is mostly complete. It covers the main purpose, the critical non-posting behavior, and the prerequisite. It does not explicitly contrast with draft_reply/draft_thread, but given the name and context, it is sufficient. The return value is hinted as a draft, and the output schema likely handles details.

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 description's contribution is minimal. It does not add meaning beyond what the schema already defines for 'topic' and 'style'. The description's mention of 'original tweet' and 'in your voice' relates to behavior rather than specific parameter semantics. Thus, a baseline of 3 is appropriate.

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 clearly states it drafts an original tweet using AI, with a specific verb ('draft') and resource ('tweet'). It distinguishes itself from post_tweet by explicitly noting it does not post automatically, and the phrase 'in your voice' adds a unique characteristic. This separates it from sibling drafting tools like draft_reply and draft_thread.

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?

It provides explicit when-not-to-use guidance by stating 'Use post_tweet() to post' and clarifies this tool only produces a draft. It also warns about the API key requirement. However, it does not compare with draft_reply or draft_thread, which could be relevant alternatives for reply or thread scenarios.

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