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

Annotations already cover read-only safety. The description adds real behavioral context beyond them: cursor-based pagination, the visibility rule that archived/private requests and internal comments remain visible to the managing team, the members.manage requirement, and a prompt-injection warning about public-authored text.

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 resource and scope, then pagination, permissions, and the safety note. Every sentence carries information an agent needs.

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?

With no output schema, the description covers the essentials: what is returned (history text, newest first), pagination, permissions, and the public-authored caution. It stops short of describing the response envelope, which would round it out.

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 60%, so the description must contribute. It clarifies the kind selection intent and cursor-following, and 'newest first' explains the implicit ordering used by the cursor's created_at. It leaves limit unaddressed, but adds enough meaning over the schema to justify a 4.

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 ('Read') and resource ('one customer's request, vote or comment history in this account'), with scope (one customer, per-account) and ordering (newest first). An agent can distinguish it from get_person and the list_* siblings without opening the 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?

Gives concrete usage direction: 'Choose a kind and follow next_cursor for more' and the auth prerequisite 'Requires members.manage'. It does not name a competing sibling or state when not to use it, so it stops short of full alternative routing.

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