research_and_stage

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

The description adds value beyond annotations: it explains the 'keyless heuristic', 'persona-aware' LLM usage, that replies are staged as drafts, and the requirement for the 'llm' block. Annotations already indicate mutability (readOnlyHint=false), and the description aligns without contradiction. It does not address rate limits or auth, but overall provides good behavioral context.

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 concise (two sentences), front-loaded with core actions, and avoids redundancy. Every sentence contributes essential information: search, filter, generate, stage, review instructions, and requirements.

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?

The description covers the multi-step workflow, staging behavior, and required configuration. With an output schema present, return values are handled. It could be more explicit about the number of drafts (linked to max_items) and the 'keyless heuristic', but overall provides sufficient context for an agent to understand the tool's role.

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%, so description must compensate. It explains 'keywords' and implies 'account' via 'Search each keyword' and 'write a reply per tweet', but 'max_items' is unmentioned. No details on the filtering heuristic or account selection logic. The description adds partial meaning but leaves key parameter semantics unclear.

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 the tool searches keywords, filters tweets, writes replies using LLM, and stages drafts. It distinguishes from siblings like 'reply_to_tweet' (which posts) by emphasizing 'Nothing is posted' and directing to 'list_drafts' for review. The action flow is specific and well-defined.

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?

The description provides clear context: use this tool for bulk research and drafting without posting. It implicitly differentiates from siblings by noting the draft staging and review workflow. However, it lacks explicit 'when not to use' or direct comparisons to similar tools like 'prepare_reply', leaving some ambiguity for agents.

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