set_contact_preferences

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description adds real value by explaining that this is a full replacement (not a merge) and that passing {} reverts to global values — critical for a destructive override. The privacy note ('Stored privately, never on the connection') and the scope disclaimer about messages/sharing/checkpoints/scheduler further bound the blast radius, though the last clause is a bit ambiguous.

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 core semantics are front-loaded in the first clause, but the second line reads as a disjointed fragment ('No messages, sharing, checkpoints or scheduler edits') whose meaning is unclear without more context. It is compact with no padding, but the structure could be tighter.

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?

This is a destructive mutation with 4 parameters at 0% schema coverage, including an obscure expected_peer_userids safety parameter. An output schema exists, so return values needn't be explained, but the description omits what data_type and peer_userid mean and how expected_peer_userids guards concurrency — significant gaps for a destructive write.

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 0% across 4 parameters, including a nested 'overrides' object, so the description carries the full burden. It only explains the overrides parameter ({} restores globals); data_type, peer_userid, and especially expected_peer_userids (a concurrency/locking parameter) are left entirely 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?

States a specific verb and resource: 'Replace this contact's preference overrides', which clearly separates it from the read-only sibling get_contact_preferences. It does not explicitly name the sibling as an alternative, but the operation is unambiguous.

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?

'at the user's request' gives a light trigger condition, and '{} restores the global values' explains the reset case. However, there is no explicit guidance on when to call this versus get_contact_preferences or how it interacts with set_contact_status, leaving usage implied rather than stated.

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