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

Annotations already declare readOnlyHint=true, and the description complements this by specifying behavioral details: 'newest first, 20 per page' and the null-state behavior of responseCategory during AI categorization. It also clarifies the tool's scope ('This tool only lists'), reinforcing the read-only nature. These details add value beyond the annotations without contradicting them.

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 compact, with the core purpose and behavior stated in the first sentence, followed by filtering options, the null-state caveat, and the workflow routing. Every sentence contributes information; there is no fluff or redundancy. It is appropriately front-loaded and efficiently structured.

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 read-only list tool with six optional parameters, no output schema, and read-only annotations, the description covers all essential aspects: what is returned (inbound emails), ordering, pagination default, available filters, a special null state, and the intended follow-up workflow. Nothing critical is missing for an agent to call this tool correctly.

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 description coverage is 100%, so the baseline is 3. The description does mention the filtering dimensions ('AI response category, campaign, lead or a time floor') which maps to category, campaignId, leadId, and since parameters, but it does not add new meanings beyond what the schema already documents. The page and limit parameters are self-explanatory from the schema, so no extra explanation is needed. The description adds minimal semantic value over the schema.

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 states a specific verb ('lists') and resource ('inbound emails (replies received from prospects)') with clear scoping ('in the workspace'). It differentiates itself from the workflow tools list_reply_drafts, update_reply_draft, and send_reply_draft by explicitly stating 'This tool only lists' and referencing the follow-up actions. This makes it unambiguous which tool to pick for listing replies.

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 explicitly frames the intended workflow: to answer a reply, first list replies, then review the AI draft, edit, and send. It names the specific sibling tools for each subsequent step, effectively instructing when to use this tool vs. the alternatives. The statement 'This tool only lists' serves as a clear exclusion, preventing misuse for drafting or sending.

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