Capture the current month's posture snapshot for an organization. The scheduled snapshot runs on the 1st; only one is allowed per month, so a second request returns 409.
Take this month's posture snapshot now (write — editor). The schedule takes one on the 1st; a month has one snapshot, so a second is refused (409).
| Name | Required | Description | Default |
|---|---|---|---|
| org_id | Yes | Organization UUID — obtain from scf_list_organizations |
Changes observed during successful MCP inspections.
v3.7.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only give readOnlyHint=false and destructiveHint=false. The description adds real behavioral context beyond that: it is a write requiring editor permission, a month contains exactly one snapshot, and a redundant call is refused with HTTP 409. Those are the facts an agent needs to avoid a failed or duplicated call.
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?
Two tight sentences: the action and its permission level are front-loaded, followed by the scheduling rule and the 409 consequence. No filler, and every clause carries operational information.
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-parameter action tool with no output schema, the description covers the essential call-time facts: write semantics, required role, the one-per-month uniqueness rule, and the failure code. Nothing needed to invoke it correctly is missing.
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?
One parameter (org_id) with 100% schema description coverage including its UUID format and a pointer to scf_list_organizations. The description contributes no additional parameter meaning, so the baseline of 3 applies since the schema already does the work.
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+resource+scope: 'Take this month's posture snapshot now.' It is clearly distinguished from the sibling read tools scf_list_posture_snapshots and scf_get_posture_snapshot, which fetch rather than create. An agent can tell immediately this is the on-demand creation action.
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 conveys when to use it (take it now rather than waiting) and names the alternative path — 'The schedule takes one on the 1st' — plus the blocking condition that a month already has a snapshot. There is no explicit 'do not use this when' clause, but the practical trigger is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.