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

Without any annotations, the description still tells the agent that nothing is sent here and that re-drafting overwrites the open draft, which is the key side-effect disclaimer. It doesn't mention permission requirements or what happens when no saved recording exists, leaving a small gap for a tool with no annotation coverage.

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 short sentences, no filler, and the core action and its 'nothing is sent' constraint are front-loaded. Every sentence contributes either parameter guidance or workflow routing.

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?

With only three parameters, one required, and output schema already documenting the return, the description covers the action, the fallback behavior for what_we_saw, and the edit/approve workflow. Nothing essential for correct invocation is missing.

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 0%, so the description carries the burden, and it does clarify what_we_saw: pass it in the worker's own words or omit it to fall back on measurements from a saved recording, which the schema's bare array-of-strings type does not convey. next_step is only named without further explanation, and visit_id is left implicit, so it isn't fully compensating for the coverage gap.

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?

The description opens with a specific verb and resource: 'Draft the recap email for the customer after a visit.' It also names the two adjacent recap tools (visits.editRecap, visits.approveRecap), so an agent can tell this tool apart from its closest sibling without opening either 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?

It spells out the trigger conditions and the alternatives: show the draft, edit it via visits.editRecap, send only after approval via visits.approveRecap. It also tells the agent that a second draft call replaces the open draft, which is exactly the kind of routing rule that changes how the tool is invoked.

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