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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the meaningful mutual-exclusivity constraint, but says nothing about what happens if more than one filter is supplied (error? ignored?) or the fact that the server returns the full list before local truncation.

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?

One compact sentence with the scope constraint front-loaded. The trailing 'client / get_clients' token is clutter that earns nothing for the agent.

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?

For a simple read-only list tool with full schema coverage and annotations, the essentials are present. Still missing: behavior on conflicting filters, and any hint that results are truncated client-side (the limit description mentions it, but the description does not reinforce it) or how it relates to search_clients.

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%, so parameter meanings are already documented. The description adds value beyond the schema by stating that client_id, first_name and parent_id are mutually exclusive and that parent_id enumerates a client's contacts — the schema alone would let an agent pass all three.

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 and resource ('List clients (customers)') and adds the distinguishing constraint that at most one filter may be used. It does not differentiate itself from the sibling vision_search_clients, so the boundary between 'list' and 'search' is left unclear.

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 'at most ONE filter' rule with the three allowed filter kinds gives real usage context, but there is no guidance on when to pick this over vision_search_clients (which presumably handles fuzzy/text filters). The trailing 'client / get_clients' is an opaque reference that doesn't help an agent decide.

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