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

High-value disclosure beyond the annotations: annotations only flag destructiveHint=true, while the description explains exactly what is destroyed (any label omitted from the list) and a recovery workflow via get_conversation. Note a tension with idempotentHint=false – set-to-exactly-list semantics are arguably idempotent, so the annotation may be mislabeled, but the description itself does not misstate behavior.

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 sentences, both earning their place, with the operation's true semantics front-loaded before the recovery advice. No filler.

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 and annotations covering the safety profile, the description supplies the decisive behavioral detail (replace semantics) plus a practical recovery path. Only minor gap is the absence of an alternate-tool exclusion.

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 the baseline is 3, and the description adds real meaning on top: the 'labels' array is not additive but declarative and complete, which the schema description ('Array of labels') does not convey.

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?

Names a specific verb and resource and then immediately corrects the misleading name: 'Sets the labels ... to exactly the list sent.' An agent can tell this is a replace operation, not an append, without opening the schema, which distinguishes it from sibling 'add_*' tools like contact_add_labels.

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 concrete usage guidance ('send the current labels (from get_conversation) with the new ones to keep them'), naming the sibling tool that supplies the current state. It lacks an explicit when-not clause (e.g. when to use update_conversation or delete_label instead), so it stops short of a 5.

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