email_agentic_assist

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

Discloses use of host LLM sampling and optional Anthropic fallback, which is behavioral info. However, it omits what the tool returns (plan vs. execution) and side effects, given no 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?

Two sentences, front-loaded with main purpose. No wasted words, but could be slightly more informative without lengthening.

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?

Lacks essential details: output format (despite output schema existence), prerequisites, and clarification that it only plans, not executes. Given complexity of LLM-assisted planning, coverage is insufficient.

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?

Input schema has one 'goal' parameter with 0% description coverage. The description implies goal is the workflow objective, but provides no format guidance or examples, requiring compensation.

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?

Description states it plans a multi-step email workflow using sampling, which is a specific verb+resource. It distinguishes from siblings like send_email or check_inbox, but could be more explicit about what constitutes a workflow.

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?

No clear guidance on when to use this tool versus alternatives like send_email or suggest_email_subject. The description only explains technical behavior (sampling/fallback), not usage context.

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