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

Adds substantial context beyond annotations: the call is metered and can consume Agent credits, a successful observation yields a portable evidence bundle, and it never broadcasts a transaction. That cost and safety disclosure is exactly what annotations cannot convey. The 'send an idempotency key' advice sits in mild tension with idempotentHint=false, but is better read as caller-managed deduplication rather than a contradiction.

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?

Four short sentences, front-loaded with the action and scope, then cost, then the non-broadcast guarantee. Every sentence carries information; the phrasing of 'includes its first portable evidence bundle' is slightly roundabout but still useful.

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?

An output schema exists, so return values need not be explained, and cost, idempotency, and non-broadcast safety are all covered. What's missing is workflow context: observation is clearly asynchronous, yet the description never points to priorseal_get_observation_job for polling or priorseal_get_evidence_bundle for retrieval.

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% at the top level but the single nested 'input' object is opaque, so the description carries real weight by revealing that the request should include an idempotency key and that it targets an existing transaction. It still doesn't sketch the nested request shape, so it improves on the schema without fully substituting for it.

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 — persisting an observation request for an already-submitted EVM or Solana transaction — and the 'already-submitted' qualifier implicitly separates it from prepare_controlled_execution. It does not name a specific sibling, so differentiation requires inference from the workflow, but the operation itself is unambiguous.

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 'already-submitted' precondition tells the agent this is a post-submission step, not a submission step, which is real routing guidance. It also warns that credits may be consumed and instructs sending an idempotency key. It stops short of naming alternatives (e.g., priorseal_prepare_controlled_execution for unsubmitted transactions, priorseal_get_observation_job for polling).

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