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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds that results are a bounded tenant set and cautions against full dumps, but does not explain pagination behavior or result completeness beyond what the output schema likely covers.

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?

Two sentences with no wasted text, and the core behavior is front-loaded. The 'APP:' prefix is slightly awkward but does not materially hurt readability.

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 output schema can carry return-value semantics, and the annotations cover safety, but the description leaves pagination and campaign scoping unexplained for a listing tool with three undocumented parameters. It is adequate for a simple read but incomplete for correct paging and filtering.

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 description coverage is 0%, and the description mentions none of the three parameters (limit, offset, campaignId). With no required parameters, the tool is callable, but an agent gets no description of how to paginate, cap results, or scope by campaign.

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 clear verb and resource: reads a bounded set of tenant contacts. This distinguishes it from single-contact getters, though it does not differentiate from other list_* siblings such as list_campaigns or list_replies.

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 phrase 'Prefer counts/samples over dumping full lists into the agent' implies a usage preference for lightweight retrieval, but it does not name alternatives, prerequisites, or when-not conditions. The guidance is indirect rather than explicit routing.

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