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

The description discloses crucial behaviors beyond the annotations: not_interested irreversibly suppresses the contact and removes them from active campaigns, provider sync happens in the background with a defined set of sync statuses, and dry_run reserves nothing and may differ from a later execution. This level of side-effect and async-behavior disclosure is exemplary and consistent with the destructiveHint and idempotentHint annotations.

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 dense but efficiently organized: purpose and statuses first, then input provenance, irreversible side effects, background sync behavior, and dry-run semantics. Every sentence carries useful information and there is no filler or repetition of schema 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?

For a mutating tool with irreversible consequences and no output schema, the description covers the needed behavioral context well: inputs, side effects, sync behavior, and dry-run output. The only notable gap is that it does not explicitly describe the shape of a successful non-dry-run response, though the mention of provider_sync_status partially addresses this.

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 only 25% schema description coverage, the description compensates well: it explains the real-world meaning of status values, identifies the provenance of campaign_lead_id, and defines dry_run semantics precisely. The idempotency_key is less elaborated in the description, but the schema already documents it as a stable retry key and the description flags the operation as idempotent.

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 states a specific action ('Record a campaign lead's interest status') and enumerates all six allowed status values, making the tool's purpose unmistakable. It also ties the primary input to get_reply, clearly distinguishing this status-recording tool from sibling read/reply tools. The parenthetical 'free, idempotent' is slightly ambiguous but does not obscure the core function.

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 gives contextual usage guidance: use campaign_lead_id exposed by get_reply, use dry_run for an advisory check, and use not_interested when permanent suppression is intended. It does not explicitly state when not to use the tool or name alternatives, but no sibling tool performs this same status-setting function, so the implied workflow is reasonably clear.

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