Send an email from support@acme.com by providing recipient, subject, and body; Squidbrake can hold risky sends for human approval and log the decision.
Send an email from support@acme.com.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | ||
| body | Yes | ||
| subject | Yes | ||
| justification | No | Why you are making this call, in one sentence. The person who approves it reads this; some calls need it. |
Changes observed during successful MCP inspections.
v0.13.0Input schema / properties / justificationAdded value: +{
+ "description": "Why you are making this call, in one sentence. The person who approves it reads this; some calls need it.",
+ "type": "string"
+}v0.3.8Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations and no output schema, so the description carries the full behavioral burden and does not meet it. It omits whether sending is irreversible, whether the message is queued or delivered immediately, whether approval is required, and what the result looks like — the schema's own 'justification' field hints at an approval flow the description never explains.
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?
One short, front-loaded sentence with no filler — structurally clean and immediately readable. It is efficient, though the brevity comes at the cost of the guidance and behavior details a send tool needs.
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 mutation tool with zero annotations, no output schema, and 25% parameter coverage, the description is far too thin. It never addresses irreversibility, approval requirements, or return behavior, leaving real gaps for an agent deciding whether and how to invoke 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 coverage is 25%: only 'justification' is documented, and the description adds nothing about any parameter. It doesn't clarify whether 'to' accepts multiple recipients, whether 'body' is plain text or HTML, or how the approval-related 'justification' interacts with sending.
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 states a specific verb+resource ('Send an email') and pins down the sender identity (support@acme.com), which is genuinely useful scoping information an agent cannot infer. It doesn't need to distinguish itself from siblings since no other sibling sends email, but it says nothing about scope (single vs. bulk, who may be addressed).
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?
There is no when-to-use guidance, no prerequisites, and no mention of the approval/decision siblings (acme_check_approval, acme_ask_user, acme_recent_decisions) that appear adjacent to this tool. An agent gets no signal about whether an approval step must precede a send.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.