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

Annotations declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the description's real added value is that the sync 'runs in the background' and is not immediately complete. That async/latency disclosure plus the verification step is genuinely beyond what annotations provide, though it does not describe failure modes or how long results take to appear beyond 'a minute or two'.

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?

Two tight sentences: purpose and scope first, async behavior and verification second. Nothing is wasted and the most important action is front-loaded.

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 no return-value documentation, the description supplies the essential async model and how to check success, which is what an agent needs. The only notable gap is not mentioning that a flagged 'hard to undo' action may require confirm=true, though the schema covers that case.

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 100%, so both parameters are already documented, including connection_id's provenance from get_program. The description adds no syntax or format detail beyond the schema, and the 'confirm' parameter's interaction with a destructive-ish guard is left entirely to the schema, giving the baseline 3.

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 ('Queue an immediate sync of an affiliate program connection') and names the exact data surfaces touched (roster, signup matching, sales stats). It is clearly distinguishable from the sibling read tool get_program, which is referenced as the verification path rather than as the actor.

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?

Gives clear context for when to reach for this tool (a manual 'Sync now' trigger) and how to confirm the result via get_program's last_synced_at. It stops short of explicit when-not-to-use guidance, e.g. avoiding repeated calls while a sync is already in flight, so it does not reach 5.

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