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

Beyond the annotations (openWorldHint=true, destructiveHint=false), the description discloses several surprising behaviors: it rotates signer tokens so 'every link emailed to them earlier stops working,' it operates 'platform-wide, never scoped to the caller's company,' and dry_run 'reports the would-be sends without emailing, rotating, or persisting anything.' These details give the agent a clear mental model of side effects and boundaries.

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 moderately long but every sentence contributes essential information: scope, exclusions, cadence cap, token rotation, invocation mode, and dry-run behavior. There is minor redundancy (platform-wide/unscoped repetition), but the structure is logical and front-loaded with the core action. It earns its length given the tool's complexity.

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?

The description covers all important operational aspects for this complex global operation: what it acts on, what it excludes, cadence limits, side effects, scheduling context, and dry-run mode. Since an output schema exists, the response format ('lists their emails') is mentioned without over-explaining. The tool feels fully specified for an agent to call safely.

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?

With zero schema description coverage, the description compensates by explaining the sole parameter dryRun in functional terms: 'dry_run reports the would-be sends without emailing, rotating, or persisting anything.' This conveys the semantic meaning and safety implications of the boolean, going beyond the schema's bare type declaration. It doesn't specify the default value, but that is not critical for a single optional flag.

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 uses a specific verb 'sweeps' and identifies the resource ('every Lovie Sign envelope awaiting signature') plus the exact action ('re-emails the signing link to the signers whose turn it currently is'). It clearly distinguishes itself from sibling tools by excluding Docusign envelopes and noting the platform-wide scope, making its purpose unmistakable.

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 states that the tool 'runs on the syncer cron' and is 'reviewer-invokable for a manual sweep,' providing clear context for when it is used. It also explains why Docusign envelopes are excluded (they run their own reminders), effectively indicating when this tool is not applicable. It doesn't explicitly name alternative tools, but the operational guidance is sufficient for agent selection.

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