Who writes to me

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely non-structured behavior: result ordering (most messages first), the specific aggregate fields produced, and the reverse semantics when folder=`sent` (counts recipients instead of senders).

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, both load-bearing: the first front-loads the output contract and ordering, the second covers the folder inversion. No filler, no restating of the title or name.

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?

An output schema exists so return values need no further explanation, annotations cover the safety profile, and 86% of parameters are schema-documented. The description supplies the remaining semantic gaps (ordering, sent-folder inversion, period scoping), so an agent has everything needed to call it 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 coverage is 86%, so the schema carries most parameters. The description still adds meaning the schema lacks, notably that folder=`sent` inverts the tool to count people the user wrote to, and it frames the since/until pair as the 'period' the tool scopes to.

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 gives a specific resource (senders) and enumerates exactly what the aggregation returns: message counts, unread counts, latest subject/time, latest message id, sorted most-messages-first. That precision implicitly separates it from search_messages and find_people, but no sibling is named outright, so it stops short of the top mark.

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?

Three concrete question phrasings ('who wrote to me this week', 'who is waiting for an answer', 'find the person from accounting who sent the invoice') tell the agent when this tool fits, and the folder=`sent` sentence flags a non-obvious alternate mode. No when-not guidance or explicit alternative is given, though.

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