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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds that pagination is 'bounded' and that MCP approval requirements are administrator-configurable while business workflow approvals always apply — meaningful context — but it never states that results are restricted to the caller's authorized records, a key behavioral trait that only surfaces indirectly in the id parameter description.

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 first two sentences are largely redundant with each other and with the title, and the closing sentence about approval configuration is generic boilerplate that consumes space without guiding invocation. The one substantive phrase ('bounded pagination and search') is buried mid-paragraph rather than front-loaded.

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, so return values need not be explained. However, for a six-parameter list tool with filtering by id, siteId, and status, the description omits the filter surface entirely and leaves pagination bounds unspecified — information an agent needs to call it correctly.

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 only 33%: id and siteId are documented, but limit, offset, search, and status are not. The description's 'Supports bounded pagination and search' gestures at limit/offset/search without giving bounds (default 50, max 100) or filter syntax, and it never mentions status or id/siteId filtering, so it does not compensate for the coverage gap.

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 verb and resource ('List sites in your organization') with clear scope. It does not distinguish itself from adjacent siblings such as get_site, create_site, or list_site_budgets, and the opening sentence ('Use this when working with RetailHardHat sites records') restates the resource rather than adding differentiation.

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?

Usage is only implied by 'Use this when working with RetailHardHat sites records in the connected organization.' There is no guidance on when to prefer get_site for a single record, or how to choose between this and the many other list_* tools. No exclusions or prerequisites are stated.

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