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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses the actual behavior: values are extracted with provenance back to the buyer's words, conflicting/unclear facts are consolidated into a single clarifying question, and unread text is retained verbatim. It also explicitly negates the most dangerous misreading — that this places an order — which the annotations alone cannot convey.

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?

The core action and its purpose are front-loaded in the first clause, followed by behavior, continuation, safety boundary, and the sibling alternative in descending priority. It is dense but every sentence carries distinct information; the parenthetical about word provenance is the only slightly costly construction.

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 no output schema, the description still tells the agent what comes back (a structured requirement with word-level provenance, or one consolidated question) and how to continue a session via id/token. For a stateful, nested-object tool this covers everything needed to invoke it correctly, including the send-vs-interpret boundary.

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 100%, so the baseline is 3, but the description adds real meaning beyond it for the nested requirement object: it is the continuation handle from a prior answer, with the token doubling as the receipt token of the sent request. turn_id and timezone are left to their schema descriptions, which already explain retry-once and date-reading purposes.

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 gives a specific verb and resource — handing the buyer's free-text requirement (or a correction/addition) to Joinery to be read into a structured requirement — and immediately distinguishes it from send_requirement (dispatch) and submit_request (already-structured fields). An agent can route between these three without opening any 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 states when to use this tool (natural-language requirement, corrections, additions), when not to (structured fields already in hand -> submit_request), and what must not be assumed (nothing is sent/ordered; send_requirement does that). The continuation rule — pass the requirement id/token from the first answer — is spelled out explicitly.

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