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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the description's job is to explain what gets overwritten — and it does: 'The same address again changes that one' discloses upsert semantics keyed on URL. It also discloses the deferred behavior that metrics are only read after owner confirmation, which is real context the annotations cannot convey. It stops short of stating failure behavior for unsupported platforms or what is returned on success.

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?

Three short sentences, front-loaded with the action and platform scope, followed by the post-add behavior and the upsert rule. No filler, and each sentence carries distinct information.

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 single-parameter tool with a fully documented nested schema and no output schema, the description covers purpose, keying, and post-call behavior adequately. The remaining gap is edge-case handling — unsupported platform strings (no enum in the schema) and what confirmation failure means for the added accounts.

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, but the description adds genuine meaning: the URL is the identity/dedupe key ('each by its profile's address', 'The same address again changes that one'), which is not stated in the schema. It also implicitly supports the optional handle field by talking about profiles rather than handles.

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 ('Adds the business's own social accounts') and enumerates the platforms covered, which distinguishes it from the many other add_* siblings (add_logo, add_places, add_products, add_font). It also clarifies the unit of input ('each by its profile's address'), so an agent knows one call carries one or more accounts.

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?

Usage is implied rather than spelled out: 'Marsell reads their numbers once the owner confirms' hints that this registers accounts for later data collection pending owner confirmation, but there is no explicit when-to-use or when-not guidance. No alternative sibling is named for adding or updating a social account, though the description does note that re-submitting the same address updates instead of duplicating.

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