zabbix_delete_maintenance

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

Annotations already declare destructiveHint=true and non-idempotent, but the description goes further: it states the operation is IRREVERSIBLE with no undo, explains exactly what dry_run returns (the window's full definition), and discloses that the BEFORE definition is captured in priorState. That is meaningful behavioral context an agent cannot derive from the annotations alone.

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?

Risk tag and irreversibility warning are front-loaded, followed by the dry-run contract, the priorState return note, and a tight three-line Args block. No sentence is wasted, and the most consequential fact (no undo) comes before anything else.

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 high-risk destructive tool with no output schema and no parameter documentation in the schema, the description covers risk, reversibility, dry-run preview behavior, where to source the id, and what gets captured on execution. An agent has everything needed to call it safely.

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 0%, so the description carries the full burden and does: maintenance_id is identified as coming from zabbix_maintenances, dry_run is defined as preview-without-deleting, and target is explained as a config target name with omission meaning the default. All three parameters gain semantics absent from 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 ('Delete a Zabbix maintenance window') and scopes it to Zabbix, placing it clearly apart from zabbix_maintenances, zabbix_create_maintenance and the PRTG/SolarWinds maintenance siblings. The risk tag signals impact immediately.

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 a clear usage path: pass dry_run=True to preview before committing, and obtain the id from zabbix_maintenances. It does not explicitly name when to prefer zabbix_create_maintenance versus a maintenance window edit, but the delete context is unambiguous for this tool.

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