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

With no annotations, the description carries the full burden and mostly succeeds: it discloses the authentication model (customer must sign in with an email on file; a forwarded URL exposes nothing), that the URL is returned only once and is not re-retrievable, the lifetime default/ceiling and revocability, and the required role. It does not say whether multiple live links can coexist or whether creating one invalidates a prior link, which is a real gap for a link-minting mutation.

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?

Purpose is front-loaded in the first clause and each subsequent sentence adds a distinct operational fact (auth model, one-time URL, lifetime, permissions) with no filler. The feature enumeration in sentence one is slightly long but is doing real explanatory work for an unfamiliar 'hub' concept.

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 the return shape needs no prose, and the description still flags the critical property that the URL appears only once. Combined with the auth model, expiry, and role restriction, an agent has enough to invoke it correctly; only the link-lifecycle question (one active link vs many) is unanswered.

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%, so the description must compensate, and it does for the non-obvious parameter: 'expires_in_days (default 90, up to 365)' adds the default that the schema omits entirely and frames revocation semantics. customer_id is left implicit, but it is the sole required field and its meaning is self-evident in context.

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?

Opens with a concrete verb+resource ('Make a customer hub link') and spends a sentence defining what the artifact actually is (a single page showing quotes, jobs, invoices, visits, requests). That is far more than the name conveys. It stops short of naming hub_links/hub_revokeLink, so an agent must infer the boundary with siblings on its own.

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?

The use context is unambiguous: give a customer a self-service page to view work, pay, and request changes. It states a hard precondition ('Owner or office only') and an operational instruction ('send it to the customer yourself'), which guides invocation. No explicit when-not or named alternative (e.g. hub_links to inspect existing links), so it falls 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.