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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds real behavioral detail beyond that: a hard cap of 50 returned profiles and ordering by newest update first. It stops short of stating what happens on no match or whether results can be paged.

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?

Three short sentences, zero filler, with the identifier requirement and result limits front-loaded. 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 partially compensates by describing result count and sort order. It is nearly complete for a simple lookup, though it omits behavior on zero results and any pagination or truncation semantics for the 50-cap.

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?

With 100% schema description coverage, the params are already documented, including the E.164 example and the 'older Lookup Adaptors' caveat. The description's only added value is the cross-parameter mutual-exclusivity constraint, which is notable but largely mirrors schema text otherwise.

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 ('Find customer profiles') plus the lookup keys, so the agent knows it is an identifier-based lookup rather than a list. It does not distinguish itself from the sibling gladly_get_customer, leaving ambiguity about which of the two retrieves a profile.

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 'EXACTLY ONE identifier' rule is genuinely useful call guidance, especially since the schema marks all three params optional and enforces no oneOf. However, it gives no when-to-use versus gladly_get_customer or gladly_list_customer_conversations, so routing between siblings is left to inference.

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