Draft a client message

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

With no annotations, the description carries the full burden and does the important part well: 'Nothing is ever sent or written to Jobber - the draft is returned for human review,' which rules out the main side-effect risk. It also discloses that facts are pulled live rather than from cached/stale data. It stops short of covering failure behavior (invalid client_id/invoice_id, missing facts) or auth requirements.

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 sentences, front-loaded with the core action and the no-side-effects guarantee, then the message-vs-template conditional. No filler, no restating of the title, and every clause carries information an agent needs before invoking.

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 an 8-parameter tool with no annotations, the description covers purpose, mode selection, and side-effect safety, which is the bulk of what's needed. The remaining gap is the return shape: there is no output schema, and the description only says 'the draft is returned' without indicating whether verified facts or a rendered template come back alongside it.

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 100%, so the baseline is 3 and the schema already documents all 8 parameters. The description adds real meaning on top: `message` is 'used verbatim' and suppresses template generation, while `purpose` drives template selection, and `invoice_id` facts matter mainly for payment reminders. That interaction between parameters is not in the schema.

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 ('Compose a DRAFT message (email or SMS) to a client') and immediately scopes it as draft-only, distinguishing it from any send action. It also names the concrete enrichment source (Jobber invoice number, balance owing, due date, days overdue, client name), so an agent knows exactly what this tool produces.

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 branch: 'Provide `message` if you already wrote the body ... omit it to get a template based on `purpose`.' That tells the agent when to use which mode. It doesn't name alternatives among the siblings (e.g. fetch facts with get_unpaid_invoices first), but no sibling actually overlaps this compose capability.

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