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

Goes well beyond the destructiveHint/idempotentHint annotations by enumerating concrete consequences: the project disappears from list_projects and the app, scheduled posts stop going out, and a connected YouTube channel is disconnected. It also discloses what is preserved (posts and profile) and the restoration path, which is exactly the behavioral context an agent needs before 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?

One tightly packed sentence covers effects, persistence, reversibility, and the consent instruction, with the irreversible-sounding consequences front-loaded. No filler and no repetition of structured data.

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 two-parameter destructive tool, the description covers scope of effect, side effects on linked resources, data retention, and the confirmation protocol. No output schema exists but none is needed since return behavior is not decision-relevant here.

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 100%, so projectId's meaning and origin (list_projects) and confirm's consent requirement are already documented in the schema. The description reinforces the confirm gate ordering but adds no new format or constraint detail, so the baseline of 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 and resource ("Archives a project") and immediately anchors it to an observable behavior the user knows ("as deleting a brand in the app does"). An agent can distinguish this from destructive siblings like delete_post and from create_project, which is named only as the undo path.

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 explicit preconditions for invocation: ask the user for consent, then pass confirm: true. It also points to create_project with reactivateProjectId for the reverse operation. It stops short of saying when NOT to archive (e.g. when the user only wants to hide scheduled posts, which unschedule_post would handle), so it is strong but not a full routing guide.

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