AgentExec WebMCP & Base L2 Gateway

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses backend-dependent result fidelity (gas and balance changes vs gas estimate only), a per-client rate limit, and the API-key/public-simulation conditions. It stops short of describing the result shape of the fallback path or what maxAllowedDrainUSD actually does when tripped.

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?

Two dense sentences with the primary behavior front-loaded and the fallback/rate-limit caveats second. Nothing is redundant, though the parenthetical load makes the first sentence slightly hard to parse.

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?

With no output schema and 0% schema coverage on five parameters, the description should cover the result shape and the drain-limit semantics; it covers the simulation paths but leaves the agent guessing about return values and the safety parameter. Adequate but with real gaps for a 5-parameter tool.

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 0% across five parameters, and the description adds no parameter meaning at all — nothing on calldata encoding, valueWei units (implied but unstated), address formats, or the maxAllowedDrainUSD safety threshold. The most safety-critical parameter is entirely undocumented in both places.

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 ('simulates a transaction') plus the key scope constraint ('without broadcasting'), which implicitly separates it from execute_onchain_intent. It never names a sibling, so the contrast must be inferred from the sibling list.

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 explains the runtime fallbacks (Tenderly vs RPC gas estimate) but never says when to call this instead of execute_onchain_intent or get_smart_account_info. Usage is implied by 'without broadcasting' rather than stated as guidance or exclusion.

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

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

Goes well beyond the annotations (destructiveHint=true, openWorldHint=true, idempotentHint=false) by disclosing the simulation strategy and its fallback (Tenderly vs RPC gas estimate plus USDC cap), that settlement occurs only after target and simulation checks pass, that payment is exact-price and single-use, and the safety instruction never to send a private key. These are exactly the operational traits an agent cannot get from structured fields.

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?

Front-loads the action and target chain in the first clause, then layers simulation, auth, and payment mechanics in a logical order. Every sentence carries operational information; there is no filler despite the density.

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?

Covers authorization, simulation, payment, and safety completely for a destructive, open-world mutation tool with 8 params. The remaining gap is that no output schema exists and the description never says what a successful execution returns (transaction hash, receipt, simulated balance changes), leaving the agent to discover the response shape.

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 the baseline is 3. The description adds workflow meaning that the schema alone does not: paymentSignature is only needed on the second call after the first call returns payment requirements, and the USDC cap semantics tie back to the simulation path. It does not explain sessionKeyId's cap-enforcement interaction with the payment flow in any depth.

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+resource ('Simulates and executes a gasless, sponsored Web3 transaction on Base L2') with concrete examples of intent types (token swaps, transfers) and scope constraints (operator-allowlisted targets). It does not name the sibling dry_run_simulation, so an agent must infer why it would pick this over that tool, but the purpose 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?

Gives clear preconditions (API key required, operator-allowlisted target, payment when operator charges) and a procedural when-to-use path for the paid case: call once, receive x402 requirements, sign locally, call again with paymentSignature. It stops short of stating when to prefer dry_run_simulation or when to route through issue_session_key instead.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description does not need to restate safety. It adds useful behavioral context by naming the Base network and noting that no API key is required, though it does not discuss error behavior or rate limits.

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 description is a single front-loaded sentence that identifies the returned data, the network, the deployment status, and the no-API-key condition. Every clause adds relevant information without waste.

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 zero-parameter read-only tool with no output schema, the description supplies the key return values and the auth condition an agent needs to decide whether to call it. Annotations cover the safety profile, and nothing critical is missing for correct invocation.

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?

The tool has zero parameters, so there are no parameter semantics to explain. The baseline score for no params is 4, and the description appropriately focuses on returned information instead of inventing parameter details.

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, 'Retrieves,' and names the exact resources: the Agent Owner EOA address, Safe Smart Wallet address on Base, and deployment status. It is clear enough to distinguish from siblings like execute_onchain_intent or dry_run_simulation by being purely informational, but it does not explicitly differentiate itself from those tools.

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 by the retrieval purpose and the note that it 'Works without an API key,' which is a useful prerequisite signal. However, the description does not state when to use this tool versus alternatives, nor does it include exclusions or when-not conditions.

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

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

Annotations already declare non-readonly, non-destructive, non-idempotent, closed-world; the description adds real context beyond that: enforcement happens at the gateway, ZeroDev on-chain permissions apply only when the operator configures them, and an API key is required. It stops short of saying what is returned or whether keys can be revoked.

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?

A single dense sentence plus a short qualifier; the core capability is front-loaded and no clause is redundant.

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?

No output schema exists, yet the description never says what an issued key looks like, its format, or how to revoke it — an agent must guess the return shape of a security-sensitive credential. Parameter and auth context are otherwise adequate for a four-parameter tool.

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 0%, so the description carries the burden, and it maps three of four parameters to meaning (ttlHours=time limit, maxUsdc=USDC spend cap, target=whitelist). Only agentId is left unexplained, which is minor given it is the single required field with an obvious name.

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 ('Issue a scoped session key') and enumerates the scope dimensions (time limit, USDC spend cap, target whitelist). This is clearly distinguishable from execute_onchain_intent and get_smart_account_info, though it never names those siblings explicitly.

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?

Implies usage as a prerequisite setup step before onchain execution and notes 'Requires an API key', but gives no explicit when-to-use/when-not guidance relative to dry_run_simulation or execute_onchain_intent, and no prerequisites beyond the API key.

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