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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: the operation is soft (records kept, list membership preserved), there is a protected-object exclusion (Primary Market ICP), and retry semantics are spelled out. It stops short of saying what happens to campaigns or audiences referencing the archived ICP, or what the response contains.

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?

Four short sentences, front-loaded with the core action before the qualifiers, with no filler. The final sentence on idempotency partially duplicates the idempotencyKey parameter description, which is the only mild redundancy.

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 destructive, nested-object mutation with no output schema, the description covers consequences and one exclusion, which is decent. However, with no return-shape documentation the agent is left guessing what a successful archive yields, and the effect on dependent entities (campaigns, audiences built from the ICP) is unstated.

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 coverage is only 33%, so the description needs to carry weight for undocumented parameters, but it mentions none of them by name. `icpId` is undocumented in the schema and the description never states that the identifier is required or where it is nested; the optional `reason` audit field is likewise absent from the description. Only the idempotencyKey behavior is reflected, and that is already documented in 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?

"Archives an ICP" is a specific verb plus resource, and the follow-up sentence clarifies what archiving means here (ICP lists retain it, records are kept), which distinguishes a soft archive from a hard delete. It does not explicitly differentiate itself from the other archive* siblings (archiveCampaign, archiveCompanyNotes, archiveSequenceTemplate), but the resource name makes the target unambiguous.

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 gives one hard precondition — the Primary Market ICP cannot be archived — which is genuinely useful routing information. It does not say when an agent should archive versus take another action (e.g., updateIcpDraft, publishIcp), nor what state an ICP must be in, so usage is only partially implied.

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