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

Annotations only declare generic hints (readOnlyHint=false, destructiveHint=false, non-idempotent, closed-world); the description adds the real behavioral detail an agent needs: a 10-minute lease re-handed out up to 3 attempts, unclaimed commands expiring after 24 h with an owner alert, one-time signed media_url handout, and the mandatory ack_meta_command follow-up. This is consistent with idempotentHint=false since claiming re-distributes work.

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?

The core action and scope are front-loaded in the first clause, followed by the command families and then lifecycle rules in a logical order. It is a dense single paragraph with a few parenthetical asides, but nearly every clause carries operational information.

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 lease/queue tool with no output schema, the description covers lifecycle, retry, expiry, and the acknowledgement path — the things that determine correct invocation. It does not indicate what a claim returns (e.g., the command payload shape) or whether repeated claims while a lease is held return anything, which is a minor remaining 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?

With 50% schema coverage, both leaf parameters (limit and fb_user.id) already carry schema descriptions, and the description adds only indirect meaning by calling the target the "tokenless Meta profile of a logged-in FB user." It says nothing about how limit interacts with the lease/batch semantics, so it adds marginal value over 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?

"Lease the Facebook writes Torvex queued..." states a specific verb (lease) and resource (queued Meta write commands) plus the scope: tokenless browser-extension profiles with no Graph token. It enumerates the command families covered (pause/resume, budget, comment moderation, graph_call/graph_upload), so an agent can tell it apart from sibling tools such as ack_meta_command or set_campaign_status.

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 clear qualifying context: use it for cabinets with no Graph token, it is what the extension polls every minute, and each claimed command must be performed in the Ads Manager session and then acknowledged with ack_meta_command. It lacks an explicit "do not use when X, use Y instead" for token-bearing cabinets, so it is strong context rather than full routing guidance.

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