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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds that it's paginated)Skip, which is critical because agents need to handle pagination properly (pageSize, pageToken). It also mentions it lists customers a company invoices, which implies it's scoped to a company, but it doesn't explicitly say it's read-only beyond the annotation. The pagination note adds behavioral context beyond annotations, so a 4 is appropriate.

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 description is two sentences, front-loaded with the core purpose, then the read-only and pagination note, then two use cases. No fluff, every word earns its place. It's efficient and well-structured for quick parsing.

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 tool is simple (list clients) and has an output schema to cover return format, so the description doesn't need to describe that. It covers the main use cases and pagination. However, it doesn't mention any default behavior (e.g., default page size) or whether the list is only for the current company. The output schema likely covers pagination metadata, so it's mostly complete. The lack of parameter semantics is a minor gap, but given the simplicity)Skip, a 4 is reasonable.

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%, meaning the description doesn't compensate for the parameters. The input schema has 3 parameters (filter, pageSize, pageToken), but the description does not explain any of them. For example, it doesn't clarify what 'query' does in filter, or how to use pageToken, or that filter supports multiple IDs. With zero coverage, the description should provide some guidance, but it doesn't, so this is a significant gap. Even though the schema itself is self-explanatory for many, the description adds no value for parameters.

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 clearly states the tool lists customers a company invoices, and it distinguishes from sibling client_get_client by specifying it's the list variant. It also mentions the resource (clients) and the action (list). This is specific and unambiguous, even though 'client' vs 'customer' terminology could be slightly clarified, but the context makes it clear.

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 description explicitly says to use this to find a client id before creating an invoice, and to answer 'who do we bill'. This provides concrete use cases and implies it should be used when you need a client id or a list of billable customers, which is distinct from other list tools in sibling tools like company_get_list_companies. It's clear when to use this tool versus alternatives.

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