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

Annotations already establish readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description contributes context the annotations cannot: a free tier of 10 calls/day followed by $0.001 per call via the HTTP endpoint or X-API-Key credits, which is exactly what an agent doing polling loops needs to know. A minor gap remains around when 'not found' should be expected (e.g., freshly broadcast transactions), which matters for polling logic.

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?

Three short sentences, front-loaded with the question the tool answers, then usage, then cost. Every sentence earns its place. The staccato fragments ('Cheap polling for agents waiting on a tx.') are efficient though slightly clipped, and the pricing detail is packed densely into one sentence.

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?

A low-complexity, two-parameter read tool with an output schema (so return values need not be explained), full schema coverage, and rich annotations. Purpose, call pattern, and cost are all present. The only thing an agent might still want — how quickly a just-broadcast tx becomes visible, or polling cadence advice — is absent but not critical.

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 100% and the chain property already lists all supported networks, so the schema carries parameter semantics fully. The only addition from the description is that confirmations/finality are chain-dependent, which is implied rather than spelled out. Baseline 3 is appropriate when the schema does the work.

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 names a specific resource (a transaction, keyed by chain + hash) and enumerates the exact outcome states it returns: pending, confirmed, reverted, not found, plus confirmations and a finality hint. That is far more than a restatement of the name. It does not explicitly contrast itself with the sibling tx_explain, so an agent must infer the split (status polling vs. decoding/explaining) on its own.

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?

'Cheap polling for agents waiting on a tx' gives a concrete usage scenario and signals the intended call pattern (repeated, low-cost). It stops short of an explicit exclusion or named alternative, so nothing tells the agent to prefer tx_explain when it actually needs calldata interpretation rather than status.

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