Chain State, Blocks & Fees

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is fully covered by structured data. The description adds no behavior beyond that: it never notes that getProgramAccounts and getBlock are expensive/large responses, says nothing about commitment levels, rate limits, or response depth, and only implicitly signals that the simulate* actions do not broadcast transactions. For a tool spanning 11 actions, that is a meaningful disclosure gap.

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?

It is compact at two sentences with no redundancy, and the routing exclusion is placed at the end where it is easy to miss. The dominant style is a comma-separated capability dump rather than a front-loaded statement of what the tool is and how to drive it, so an agent must parse the list to extract scope.

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?

Given 11 actions, 26 parameters, 12% schema coverage, and no output schema, the description is far too thin to arm an agent for correct invocation. It does establish the read-only chain-data domain and one exclusion, but leaves action selection and per-action argument requirements entirely undocumented. Complexity here warrants at least a short action-to-purpose map.

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 only 12% across 26 parameters, so the description must compensate and largely does not: there is no action-to-parameter mapping (e.g. that getBlock needs slot, getTokenAccounts needs owner or mint, simulateTransaction needs transaction, getBundleStatuses needs bundleIds). Only faint hints leak through phrases like 'stake reads' and 'priority fees' implying stakeAccount, priorityLevel, and includeAllLevels. An agent calling this cannot infer required arguments from the description at all.

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 enumerates the concrete resource families covered (raw chain state, token accounts, stake reads, blocks, network status, priority fees, simulation, bundle status), which tells an agent it is a read-only chain-data dispatcher rather than a wallet/portfolio tool. The explicit 'not wallet portfolio summaries' exclusion separates it from heliusWallet. It stops short of naming sibling alternatives like heliusTransaction, so the boundary is only partially drawn.

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?

There is one concrete routing rule: 'Use for token accounts or blocks, not wallet portfolio summaries,' which is a real when-to-use/when-not pair. However, the tool exposes 11 distinct actions and the description gives no guidance on which action to pick for a given need, nor any prerequisites or exclusions against heliusTransaction, heliusAccount, or heliusAsset. Usage is implied by the capability list rather than stated.

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