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

Annotations already declare write/idempotent/destructive/openWorld, so the description's job is to add nuance — and it does: it explains that an empty `character_uuid` performs the removal, that the effect is link-only (posts are not drawn with the character), and where the resulting state becomes visible in list_social_accounts. It does not cover permissions or failure modes, so not a 5.

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?

Front-loads the write tag and core action, then layers scope, allowed values, and parameter sourcing in short clauses with no filler. The compressed notation (pipe-delimited platform codes, backticked fields) is efficient but slightly telegraphic.

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 3-parameter write tool with no output schema, the description covers inputs, the unlink path, the non-effect on post rendering, and where to verify the result. Auth/permission requirements and error behavior are the only notable omissions.

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 0% and contains no enum, yet the description supplies the full platform value set (ig|fb|tw|tt|yt|li|th|tg|bsky) and the provenance of both UUIDs. It also defines the otherwise opaque null/empty semantics of `character_uuid` as an unlink — meaning the schema could never convey on its own.

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 ('Link one of the merchant's characters to a connected social account') and covers the inverse operation ('take it off (`character_uuid` empty)'). This is clearly distinguishable from siblings like list_social_accounts, sync_social_account, or edit_character without opening any schema.

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 routing guidance for obtaining inputs ('`account_uuid` is the account's uuid from list_social_accounts and `character_uuid` one from list_characters') and clarifies the when-not case: it does not affect how posts are rendered. It lacks an explicit statement of prerequisites or when to prefer a different tool for related account settings, 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.