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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) by stating flagging does not move or mark messages read, that flags are verified by reading back off the server with per-message failure naming, and the idempotency behavior. This is rich, non-obvious 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?

Front-loaded with the core purpose and packed with useful detail, but slightly dense and somewhat repetitive (idempotency is stated both explicitly and echoed by the annotation). Every sentence still carries substantive information.

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 2-parameter, no-output-schema state-mutation tool, the description covers purpose, invocation batching, folder scoping, verification behavior, idempotency, and the clearing alternative. Nothing an agent needs to call it correctly is missing.

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: a uid only means something in its originating folder, and `mailbox` should be passed when uids did not come from INBOX. That scoping rule is not derivable from the schema alone.

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+resource ('Flag messages') and immediately anchors it to a recognizable mental model ('the same star/flag marker Outlook and webmail show'). It also ties the state to a sibling's filter (search_emails's `flagged`), making it easy to distinguish from other mail-state tools.

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?

Gives explicit invocation guidance ('Pass the whole set in ONE call'), the mailbox-selection condition ('pass `mailbox` when the uids did not come from INBOX'), and names the clearing alternative ('unflag_email clears it'). When-to-use is grounded in 'the user's own attention' marker semantics.

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