Draft a reply (sends nothing)

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

Adds real context beyond the annotations: it consumes the workspace AI budget (a cost), returns text only and sends nothing (clarifying that destructiveHint=false means no side effects on the conversation), and requires a key with the Drafts or Publish scope. It stops short of describing length, language, or failure modes, which keeps it at a 4.

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 and each sentence carries usable information (cost, return shape, approval flow, scope). It is slightly dense at six sentences and the approval guidance could be tightened, but 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?

For a two-parameter generation tool with no output schema, the description covers what is returned (text only plus the needsPerson flag), what is not done (nothing sent), auth scope, and the follow-up tool. An agent can call and act on it correctly without opening anything else.

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 both parameters are already documented in the schema; the description only implies that conversationId refers to a single conversation and that instruction shapes tone. Baseline 3 applies when the schema does the heavy lifting.

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: ask Postfjord's AI to write a reply to one conversation in the brand voice. The parenthetical title 'sends nothing' plus 'Returns the text only' separates it cleanly from postfjord_send_reply and from the other drafting 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 workflow: show the draft to the person you work for, then send with postfjord_send_reply only after approval. Names the alternative tool and the condition that selects it, and explains the needsPerson branch for escalation.

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