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

Annotations only flag destructiveHint=true and openWorldHint=true; the description adds the async contract beyond them: merges run one at a time in the background, the call returns on queue rather than completion, and status moves 'Approved' → 'Merged' or back to 'Queued' if a pre-merge check escalates. It also names the reversal tool, giving the agent the full behavioral picture.

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 highest-value fact (the CRM merge) is front-loaded in caps, and the sentence carrying the async/status semantics earns its length. It is dense but nearly every clause adds decision-relevant information; a slight trim of the status enumeration would tighten it further.

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 carries the return-value burden and does so completely: it explains the immediate return, the eventual states, and how to observe them via get_duplicate_group. Combined with the gate condition and undo path, nothing needed to call it 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%, so both parameters are already documented (group_id must be 'Queued', connection_id directs to list_crm_connections). The description doesn't add format or syntax detail beyond the schema, so baseline 3 is correct despite the schema doing the heavy lifting.

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?

Specific verb+resource ('Approve a queued group') with the crucial scope disclosure that this MERGES IT IN THE CRM. It distinguishes itself from the siblings it could be confused with, especially get_duplicate_group (which it tells the agent to poll) and reverse_duplicate_group (the undo).

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?

States an explicit gate for use ('Only a group whose match score (rule_similarity) is 1.0 can be approved here') and names the alternative path ('below that a person approves it in the Queue'). It also tells the agent to poll get_duplicate_group to learn the outcome, covering when-not and follow-up.

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