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

Annotations already declare readOnlyHint and non-destructive, and the description still adds real behavior: the DEMO_WORKSPACE refusal, the has_link:false state and what to do about it, the fact that people_joined counts people not workspaces, and that this read will not guess a workspace. That is exactly the beyond-annotation context the score rewards.

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-loaded with purpose, then behavior, then alternatives, then multi-workspace routing — a sane ordering with each paragraph doing a distinct job. It runs long and repeats the workspace_id rule that the schema already carries, costing a point, but no sentence is pure filler.

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?

Output schema exists, so return values need not be explained, yet the description still clarifies the meaning of people_joined, last_joined_at, has_link, and the refusal code. The only gap is that conversation_id and workspace_scope — which affect multi-turn correctness — are left entirely to the schema.

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 100%, so both the workspace_id omission/requirement rule and the conversation_id and workspace_scope semantics are already documented in the schema; the description's workspace_id guidance largely restates it. The description adds nothing on conversation_id or the family scope, so it does not exceed the baseline for a fully documented schema.

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?

First sentence names the exact resource (the workspace's referral link) and the secondary figure (how many people joined with it). It also explicitly contrasts with well_get_workspace_invite_link and well_create_referral_code, so an agent can distinguish it from its closest siblings without opening a 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?

States triggering user phrasings (referral link, sponsorship link, "mon lien de parrainage"), the recovery path when has_link is false (call well_create_referral_code), and the redirect to well_get_workspace_invite_link for the adjacent need. It also tells the agent when to pass workspace_id versus calling directly, which is a routing rule, not just a hint.

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