update_monitorPATCH any monitor field: name, url, target, interval, expect, keyword, slow_ms, grace, cron, tags, sla_target, renotify, channels (alert routing)... Pause with {"status":"paused"}, resume with {"status":"new"}. Empty string clears optional fields.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Monitor id | |
| status | No | "paused" stops checking; "new" resumes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With empty annotations, the description must disclose behavioral traits itself. It adds useful context: 'Empty string clears optional fields' and status values 'paused' stops checking, 'new' resumes. However, it does not describe side effects, permission requirements, or the consequence of omitting fields beyond what PATCH implies, leaving some gaps.
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?
The description is concise, two sentences, with the core action 'PATCH any monitor field' front-loaded, followed by a list of examples and special behaviors. There is no redundant wording or unnecessary detail.
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?
The description covers many fields and the pause/resume mechanics, but lacks information on prerequisites like the need for an existing monitor, error handling, permission requirements, or expected response format. Given it is a mutation tool with no annotations or output schema, it could be more complete.
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?
The schema only documents id and status, but the description enumerates many additional patchable fields (name, url, target, interval, expect, keyword, slow_ms, grace, cron, tags, sla_target, renotify, channels) and clarifies behavior for status and empty strings. This significantly compensates for the schema's limited parameter coverage.
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 clearly states 'PATCH any monitor field' and lists a range of specific fields (name, url, target, interval, etc.), which precisely identifies the tool's function as updating existing monitors. The title 'Update / pause / resume a monitor' further disambiguates it from sibling tools like create_monitor, delete_monitor, and get_monitor.
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?
The description implies usage on existing monitors through 'PATCH any monitor field' and provides specific instructions for pausing and resuming via the status parameter, but it does not explicitly contrast this tool with alternatives like create_monitor or delete_monitor, nor does it mention prerequisites such as requiring an existing monitor ID.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource and action. There is no overlap between monitor lifecycle tools (create, get, update, delete, list), incident tools (list, ack, note), or utility tools (check_url, get_account, get_status_page). The descriptions explicitly differentiate check_url from create_monitor, eliminating confusion.
All tool names follow a consistent verb_noun pattern in lowercase snake_case: ack_incident, add_incident_note, check_url, create_monitor, delete_monitor, get_account, get_monitor, get_status_page, list_channels, list_incidents, list_monitors, update_monitor. No mixed conventions or inconsistent verb forms exist.
12 tools is well within the ideal 3-15 range for a monitoring service. Each tool serves a purposeful function without redundancy, covering monitor management, incident handling, and account/status information.
Monitor lifecycle is complete with CRUD plus list. Incidents have list, acknowledge, and note tools, which covers the core incident workflow. Minor gaps include no channel management (only list_channels) and no way to discover status pages (get_status_page requires a known slug), but these are peripheral and workable for most use cases.