Checks today’s ready journal edition and, when send is true, prints it once inside the configured morning print window; send false only verifies and shows the command.
Print today's ready edition. With send=false this only checks it and shows the print command. With send=true it prints once, inside the reader's print window. Never retry after an unclear result.
| Name | Required | Description | Default |
|---|---|---|---|
| send | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full disclosure burden and does well: it reveals that send=true causes exactly one physical print inside the reader's print window, and it explicitly warns against retrying on ambiguity, which signals non-idempotency — a critical trait an agent could not infer from the schema. It stops short of saying what happens on failure, how errors surface, or whether a printer must already be configured.
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 short sentences, no filler, with the dangerous mode (send=true) and its caution surfaced immediately after the baseline behavior. Every clause carries either a mode definition or a safety rule.
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 single-optional-boolean tool with no output schema, the description covers modes, side effects, and the retry hazard, and briefly indicates what the check returns ("shows the print command"). Gaps remain around preconditions (edition readiness, printer availability) and failure reporting, but they are modest for this complexity level.
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 define `send` — and it does, contrasting send=false (check only, show the print command) against send=true (print once). The default's consequence and the side effect of each value are fully spelled out, leaving nothing for the agent to guess.
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?
'Print today's ready edition' gives a specific verb and resource with a clear scope ("today's ready"), and the dry-run vs. real-print framing makes the effect unambiguous. It never names the nearest siblings (print_test_page, render_edition_pdf, publish_edition), so an agent must still infer which of these printing-adjacent tools to pick.
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 precisely what each mode is for — send=false checks only, send=true prints — which is real when-to-use guidance for the only decision the caller makes. It also adds an operational rule ("never retry after an unclear result") but gives no routing guidance against the sibling tools or prerequisites such as a configured printer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.