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

With annotations covering only readOnly/idempotent/openWorld, the description adds substantial non-obvious behavior: request_hash is recomputed in-handler and never rewrites the journal, a mismatch returns request_ok: false, a pre-trace row honestly reports 'unknown' rather than true, resolutions are terminal-or-honest-pending and never fabricated, and an unknown id yields a typed DECISION_NOT_FOUND refusal. This is exactly the kind of trust/verification semantics annotations cannot express.

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 free/evidentiary framing is front-loaded, but the body is a dense run-on with heavy emphasis that enumerates bundle contents already described by the output schema, so several clauses are partially redundant. The verify-block semantics earn their place, but the phrasing is more verbose than needed for a one-parameter tool.

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 single fully-documented parameter with an output schema present, the description covers use case, refusal behavior, honesty guarantees and the no-payment/no-live-call constraints, leaving little gap. Its enumeration of return contents overlaps the output schema, but nothing an agent needs to call it correctly is missing.

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% and there is a single required parameter, so the baseline is 3. The description restates the UUID-or-8-char-prefix contract already present in the schema description, adding only the behavioral consequence for a non-resolving id (DECISION_NOT_FOUND), not new format or syntax guidance.

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?

The description states a specific verb and resource: it returns the full evidentiary bundle for a single decision (record, resolution, payment leg, tape sources, verify block). It also distinguishes itself behaviorally from live-call siblings ('No live model call, no second venue'), though it never names the siblings directly. 'Lineage bundle' is jargon, but the elaboration makes the purpose concrete.

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?

Usage is implied via the use case ('everything a hostile auditor needs to reconstruct the forecast, the payment and the grade') and via contrast ('No live model call, no second venue', 'No payment required'), which hints at when to prefer this over live-call or paid tools. However, with 30+ siblings including tollbridge_decision, tollbridge_get_decision and tollbridge_get_resolution, no alternative is explicitly named or excluded, so routing is left to inference.

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