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

Annotations already carry readOnlyHint=true, so the safety profile is covered; the description adds real behavioral detail beyond that, including the pagination contract (next_offset from the previous reply) and code semantics for customer_status_state/customer_status_str. It does not mention rate limits, default page size, or whether results are sorted by default.

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?

Purpose is front-loaded, followed by the filter vocabulary, then the pagination rule and endpoint. The single run-on filter sentence is dense but every element is useful; 'GET /customer' is borderline filler for an agent that only needs arguments.

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 readOnlyHint set and no output schema, the description needs to cover invocation, filtering and paging — and it does. It omits how the response is shaped (aside from the next_offset convention) and gives no example of a combined filter, but nothing required to call the tool correctly is missing.

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% for limit/order/offset/filters, but the schema explicitly defers filter field names to the tool description ('the list tool's description names the valid ones'), and the description delivers that list including custom_1..custom_50 and decoded status codes. This is load-bearing information the agent cannot get from the schema alone, so it exceeds the baseline 3.

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 opens with a specific verb+resource ('List customers') and even defines the entity ('companies that are billed'), which immediately separates it from chargeover_get_customer, chargeover_create_customer and chargeover_update_customer. It stops short of explicitly naming a sibling or stating the search-vs-fetch distinction, so it is clear but not sibling-routed.

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: enumerating filterable fields signals that this doubles as a search tool, and 'Paged: pass next_offset as offset' gives a concrete operational instruction for continuing a result set. There is no explicit when-to-use/when-not statement and no guidance on choosing this over chargeover_get_customer for a single record.

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