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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds substantive behavior: the full status vocabulary with semantics (partial means some ads failed and points to `failures`, not_run vs unknown), and the warning that 'unknown' means no outcome was recorded so the destination should be verified before re-running. It also discloses the return shape (ad_ids, adsets vs campaign_ids/adset_ids per platform pairing), which matters since no output schema exists. It stops short of describing polling timing, pagination, or how long a transfer typically takes.

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 sentences are tightly packed, with the core action front-loaded and the status enumeration parenthetically anchored so it scans easily. The long inline list of statuses and returned id fields is dense but each clause conveys distinct meaning; no filler sentences.

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 read-only status tool with no output schema, the description covers both the input key, the full set of possible outcomes and their meanings, and the ids returned on completion. The only meaningful omissions are how to source a plan_id and expected polling cadence before completion.

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 burden for the single `plan_id` parameter. "by its plan_id" identifies it as the Bridge transfer's plan identifier, but does not say where the agent obtains one (e.g., from a launch or list_bridge_transfers response) or its format, leaving a gap for an undocumented required parameter.

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?

"Follow a copy across platforms until it is done" plus "Where a Bridge transfer is, by its plan_id" states a specific verb (poll/retrieve status), resource (Bridge transfer), and keying (plan_id). It is clearly distinguishable from list_bridge_transfers (listing) and get_bridge_stats (aggregates) without opening any 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 implies the usage context (after launching a copy, keep polling until terminal state) and gives concrete advice for the 'unknown' state — check the destination before re-running. However, it never names an alternative sibling (e.g., list_bridge_transfers to find a plan_id) or states when not to use it, so routing guidance is implied rather than explicit.

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