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

Annotations already indicate this is a non-destructive, non-idempotent write operation. The description adds valuable context: it 'Replaces any existing customer association' and explicitly lists what it does NOT do (invite, notify, publish replay, change recording permissions, start recording), which clarifies side effects beyond what annotations provide. It also notes that the result contains the linked meeting and customer.

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 front-loaded with the core action, followed by parameter constraints and behavioral notes. Every sentence adds necessary information, though the density is high. It could be slightly more scannable, but overall it is efficient and well-structured.

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 mutation tool with no output schema and rich annotations, the description covers purpose, parameter usage, side effects, and return value. The missing explanation of the 'locale' parameter is a minor gap, but the definition is otherwise complete enough for an agent to invoke the tool 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?

With 0% schema description coverage, the description must compensate. It explains the mutual exclusivity of roomId vs latest and leadId vs customer, and clarifies that 'latest:true' selects the most recent past meeting (excluding cancellations) and that named customers must be resolved uniquely. The only gap is that the 'locale' parameter is not mentioned at all, leaving one of five parameters undocumented.

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 ('Connect') and resource ('existing owned meeting and its retained recordings to a CRM customer'), including the scope ('finished meetings'). It clearly distinguishes this tool from siblings like create_meeting or get_meeting, which handle meeting lifecycle rather than CRM linking.

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 gives explicit invocation constraints: 'Use exactly one of roomId or latest:true, and exactly one of leadId or customer.' It also defines 'latest:true' semantics and warns against guessing IDs. However, it does not name an alternative tool or state when not to use this tool, leaving a small gap in comparative guidance.

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