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

Annotations already declare read-only, idempotent, non-destructive behavior, so safety is covered. The description adds real context beyond that: it mirrors fetch_leads' field set (score, scoreExplanation) and notes that `signal` is only present when the search asked for a need signal — a conditional output behavior the agent cannot learn from annotations or schema.

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?

Four tight sentences, front-loaded with the core purpose and differentiation before parameter and output caveats. Every sentence carries information; it is slightly dense but has no filler.

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 as do comprehensive annotations, so return-value and safety disclosure are not needed here. The description supplies the sibling routing, field parity, and conditional-signal context, leaving only minor operational details (like the limit default) to the schema.

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 meaning beyond the schema: it explains that leadIds resolves get_campaign_stats reply buckets (e.g. positiveLeadIds) back into named people, which the schema only describes as 'only these leads are returned'.

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 (Returns) and resource (leads of any campaign) keyed by campaignId, then immediately names the sibling it competes with (fetch_leads) and what differentiates them. An agent can distinguish it without opening either schema.

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 says when to use it vs fetch_leads: this tool reaches campaigns not started in the current session, whereas fetch_leads requires a jobId from a find_leads call in the same session. It also routes the leadIds parameter to its source (reply buckets from get_campaign_stats).

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