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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description still adds useful behavior the annotations cannot: newest-first ordering, 20-per-page default, and the fact that responseCategory is null while AI categorization is pending. It does not describe returned fields or pagination navigation limits beyond the schema's max.

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?

Front-loads what the tool does, then the filtering cap, then the null-category caveat, then the routing guidance. The final sentence is long but each clause carries actionable routing information; only the embedded parenthetical could be trimmed.

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?

With no output schema and a listing tool that is fully documented in the schema, the description covers sorting, pagination default, filter dimensions, and the null-category state, plus next-step routing. What it omits is the shape of a returned reply (fields an agent would parse), which is the one gap against a 5.

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 meaning: it groups the filters as 'AI response category, campaign, lead or a time floor' and discloses that the category value is null while categorization is pending. The only wrinkle is that it calls the field 'responseCategory' while the schema names it 'category' and lists no such parameter, a minor naming mismatch.

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 resource ('Lists inbound emails (replies received from prospects) in the workspace'), plus ordering and page size, which distinguishes it immediately from list_reply_drafts. An agent can tell exactly what this tool returns without opening the 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?

Explicitly scopes the tool ('This tool only lists') and then routes the agent to the correct alternatives with the condition for each: send_reply for writing a message manually, list_reply_drafts/update_reply_draft/send_reply_draft for the AI-draft workflow. The 'including ones with no AI draft, such as wrong_person or uncategorized' clause tells the agent when the manual path is the only option.

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