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

Annotations already establish it is a non-destructive write with no open-world access; the description goes beyond them by disclosing idempotent-like behavior ('created: false' for duplicates), account-level privacy ('picks stay private'), the required write scope, and that a default set is created on first use.

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 tight sentences with zero filler, front-loading the accepted input shapes and following with the suggestion and duplicate behaviors. The telegraphic style ('Picks stay private to the account') is efficient rather than confusing.

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?

An output schema exists, so return shape needn't be explained, yet the description still flags the 'created: false' duplicate signal. With all seven parameters optional, it conveys that at least one identifying input (handle+platform, URL, or suggestionId) is needed, though error behavior for insufficient input is left implicit.

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% and every parameter already has a description, including url-alone sufficiency, platform inference from url, and the kind default. The description restates the handle+platform vs URL choice but adds little syntax or precedence detail beyond the schema, so baseline 3 applies.

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 ('Add one person to the account's reference set') and immediately distinguishes the accepted inputs (handle+platform, profile URL, or suggestionId). It is clearly separable from siblings like references_suggest, references_remove, and references_list.

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?

Explains the suggestionId acceptance path and points to references_suggest as its source, and implies setId comes from references_list. It gives clear usage context but does not explicitly say when to prefer references_browse or reference_read over adding.

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