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

Adds substantial context beyond the annotations: an email reply arrives within one business day, step 1 saves nothing, the token expires in 10 minutes, and step 2 requires identical details. The annotations only flag non-read-only/open-world; the description supplies the actual side-effect model.

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?

Three tight sentences. Purpose and scope come first, then the two-step mechanics in call order — exactly the sequence an agent needs, with no 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?

An output schema exists, so return shape need not be described, and the two-step contract is fully covered. The remaining shortfall is the undocumented optional parameters (notably leave_empty and conversation_id), which an agent may misuse or omit incorrectly.

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 carry the load. It explains confirm_token thoroughly (purpose, 10-minute validity, matching details) but leaves leave_empty, conversation_id, location_id, team_size, company and phone completely unexplained, which is a real gap for a 10-parameter tool.

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 ("Sends a question to a CANOPY sales manager") and explicitly scopes it as "for anything the other tools don't answer, such as a specific price, a move-in date or a custom space," which cleanly separates it from the booking/location siblings.

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 an explicit two-step protocol: step 1 without confirm_token returns a preview, step 2 with confirm_token sends. It also states the gating condition plainly — "Only call step 2 after the person agrees" — leaving nothing to inference.

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