trace_transaction_with_context

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

Annotations already cover read-only/non-destructive, and the description adds substantial behavior beyond that: the TX_NOT_FOUND structured error on unknown hashes, the 'empty record' failure mode it protects against, the explicit non-performance of SC invocation arg decoding with the reason (codec not bundled), the conditional sc_install nullability, and the raw_tx_hex_length hint that routes agents to dero_get_transaction for the binary. No contradiction with annotations.

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?

Long but every sentence earns its place — this is a composite tool with no output schema, so the density is justified. The structure is optimally ordered: What → When → Input requirements → Output shape → Limitations → Error behavior. The summary is front-loaded so an agent can decide whether to read the details without scanning the whole block.

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 tool with 3 params, no output schema, and complex conditional behavior, the description is nearly complete: it documents the full output shape, the sc_install null condition, error semantics, and the known limitation on arg decoding. One small blemish: the error section says the composite returns 'a structured _meta.error' while the output shape lists only _diagnostics, leaving the relationship between the two fields slightly ambiguous for an agent parsing the response.

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%, so baseline is 3. The description adds value on top: it marks tx_hash REQUIRED with the 64-hex constraint front and center, explains the practical effect of decode=false (raw hex still comes back), and gives a use-case trigger for include_sc_context=false ('when you only need confirmation / ring info'). This exceeds the schema's mechanical definitions but is not a huge leap beyond them.

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 first sentence names a specific composite operation with concrete verbs — look up, classify, extract, stitch — and enumerates exact outputs: confirmation status (confirmed | mempool | unknown), kind (sc_install | transfer_or_invocation | coinbase | unknown), and inline SC surface for contract installs. It explicitly distinguishes itself from chaining dero_get_transaction with dero_get_sc, so an agent can tell it apart from siblings without opening their schemas.

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 provides an explicit 'When to call' section listing concrete user intents ('what is this tx', 'is this confirmed', 'what contract did this deploy'), states it should be the FIRST step, and names the alternative pattern (chaining dero_get_transaction with dero_get_sc) with reasons to prefer the composite. It also explains why the alternative is unnecessary for SC installs (source is embedded in the tx record).

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