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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds genuinely new behavior: recall flags rather than deletes, quarantines the whole transitive descendant subtree, and returns the exact set of quarantined agents. It stops short of stating reversibility, required authorization, or whether already-quarantined descendants are reported.

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, zero filler, with the cascade scope and the returned report front-loaded in that order.

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?

An output schema exists, so return-value detail is not required, and the safety annotations cover mutation risk. What is missing is material for a destructive cascade operation: the undefined 'reason' parameter, required permissions, and whether quarantine can be lifted.

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 for two parameters and documents neither. 'agent_id' is only obliquely implied by 'an agent', and the 'reason' parameter is never mentioned at all, leaving its purpose and format unknown.

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 (recall/flag) and resource (an agent), plus the crucial scope detail that it cascades to every transitive descendant. 'Recall' is an unusual term, but the description defines it immediately and no sibling tool (describe_agent, lineage, verify_*) does anything similar, so it is unambiguously distinguishable.

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?

Explains the effect but not when to reach for this over alternatives, what prerequisites exist (permissions, agent state), or when recall is inappropriate. An agent has to infer the trigger condition from the destructive consequence alone.

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