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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the lower bar applies. The description adds genuinely non-structured behavior: the server validates that every newly assigned account belongs to this brand and is still usable. It does not, however, say what happens on validation failure or how partial failures in add/remove are handled.

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?

Four short sentences, each load-bearing: purpose, mode semantics, id sourcing, server validation. No restatement of the title or padding, and the primary scope constraint 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 5-parameter mutation with no output schema and partial schema coverage, the description supplies purpose, mode semantics, upstream id sources and server-side validation. Remaining gaps are error/failure behavior and the relationship to set_linked_social_accounts, so it is strong but not fully complete.

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 60%, so the description must compensate for the undocumented profile_id and connection_ids. It does, mapping profile_id to list_publishing_profiles and connection_ids to list_social_accounts and clarifying that replace takes a complete list while add/remove take only the exact ids. brand_id sourcing is already in the schema, and user_goal and the 64-item cap are not mentioned but are minor.

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: choosing which connected accounts a publishing profile uses by default, and enumerates the three mode behaviors. It is clearly a mutation on profile-account assignment. One gap: the sibling set_linked_social_accounts is closely related and the description never distinguishes the two, so an agent must infer the boundary.

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: use profile ids from list_publishing_profiles and connection ids from list_social_accounts, and explains what each mode is for. It does not state when NOT to use this tool (e.g. versus set_linked_social_accounts or suggest_publishing_profiles), leaving the sibling boundary implicit.

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