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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds the crucial consequence beyond them: the action is irreversible and the filter settings of those subscriptions are permanently lost. That is precisely the 'what gets destroyed' information an agent needs before committing to a destructive 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?

A single sentence, front-loaded with the action and scope, with the destructive warning appended directly after. Every clause earns its place and nothing is padded.

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 one-parameter destructive mutation with no output schema, the description plus annotations cover the essentials: scope, bulk mode, and irreversibility. It stops short of noting error behavior for invalid or already-unsubscribed INNs, which is a minor but real gap.

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 100% and the single parameter's schema text already explains comma-separated INNs and the "all" sentinel. The description repeats the same "all" convention without adding syntax, limits, or failure semantics, so the baseline 3 applies.

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 (отписаться) and resource (мониторинг) plus the exact scope of operation: named INNs or everything via inn="all". The destructive inverse relationship to monitoring_subscribe is unambiguous from the name alone, so an agent can distinguish it from its monitoring siblings without opening the schema.

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 clearly establishes the two usage modes (specific INNs vs. "all" for a bulk unsubscribe), which is the decision an agent actually faces here. It does not, however, explicitly name monitoring_subscribe or monitoring_list as alternatives, nor state any when-not condition, so it falls short of full routing guidance.

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