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

With no annotations, the description carries the full burden and does well: it discloses customer-facing side effects (text plus email when on-the-way notices are on), the fallback rule (email sends whenever an address exists even if text is blocked or refused), inclusion of the ETA text when arrival notices are also on, and idempotency ('a repeat call does not send again'). It stops short of saying whether the visit record itself changes state or what happens when a worker calls for an unassigned visit.

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 the core action and an example, then permissions, then side effects. Slightly rambling with a redundant aside ('Text is the main one'), but each sentence carries actionable information and nothing is 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, and the description covers the hard parts for a mutation with no annotations: permissions, notification fan-out, and deduplication. The remaining gap is the absence of any mention of sibling tools in a very crowded visit lifecycle namespace.

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 50%: eta is described in the schema, and the description usefully clarifies it is a free-form time 'in their words' that may be omitted, reinforcing the optionality. visit_id has no schema description and none here either, and the description never states that omitting eta still fires the notification without a time, which is the one non-obvious interaction between the two params.

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: marking that a worker is on the way to a visit, with a concrete trigger example ('on my way, there by 2'). The purpose is unmistakable, but it never distinguishes itself from the near-identically-named sibling visits_onTheWay, leaving the agent to guess which one applies.

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 clear activation context ('when they tell their agent') plus explicit authorization rules: a worker may only use it for a visit they are assigned to, while the owner or office may use it for any visit in the shop. It does not name alternatives such as visits_onTheWay, visits_arrived, or visits_start, so the routing decision between sibling lifecycle tools is still inferred.

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