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

Goes far beyond the annotations: rate limit (20 assistant-started sends per workspace per day), same-day deduplication of identical sends, white-label behavior, PDF attachment default and up to two-minute render time, 'Deleted' report restriction, send-history logging, and the guarantee that AI summaries are never rewritten. The preview-vs-send safety behavior is stated precisely, which is exactly the kind of context annotations cannot carry.

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 purpose and alternative, and every clause carries real information (limits, safety, side effects) with essentially no filler. It is one dense run-on block, though; splitting the preview/confirm workflow and constraints would improve scanability without losing content.

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?

No output schema exists, yet the description tells the agent what the preview returns (recipients, subject, language, PDF, where the button leads) and what side effects a real send produces (logging, PDF attachment, dedupe). For a write tool with daily limits and a confirmation dance, 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 semantics the schema lacks: the preview→confirm→previewToken handshake, recipient validation ('every address must be valid; none is dropped silently'), and the recipient cap. The 'attachPdf' default and previewToken 15-minute validity largely duplicate the schema wording.

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 ('E-mail a report once to up to 10 recipients') and immediately anchors it to a known UI concept ('One-time email' on the Share panel), so the agent knows exactly what operation this is. It also names the sibling it is not ('Not for recurring sends (schedule_report)'), making it trivially distinguishable from schedule_report.

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 gives the when-not condition ('Not for recurring sends; use schedule_report'), the prerequisite ('Requires MCP write actions'), and the two-step confirmation workflow ('without confirm:true it returns a preview and sends nothing'). The agent knows exactly when to invoke it and when not to.

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