BaseGuard AI

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds the 'Free' pricing trait, which is genuinely new information not in annotations, plus the returned content set. It does not mention rate limits, auth requirements, or whether data is cached/live.

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 compact sentence with no filler, front-loading the pricing trait and then the payload contents. Minor cost is that 'prices' and 'payment mode' are ambiguous in a status context (prices of what asset/service), which brevity leaves unresolved.

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 status endpoint with no output schema, listing the fields it reports is close to sufficient. It stops short of describing the response shape or freshness, but annotations carry the safety semantics and there are no inputs to explain.

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 takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. The enumerated content list is the only semantic surface and it is consistent with an empty schema.

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 exactly what the tool surfaces (service health, payment mode, networks, prices, Bazaar indexing), which makes the resource concrete and unambiguous. It lacks an explicit verb and never contrasts itself with siblings like base_preflight or base_risk_delta, so an agent can't fully tell it apart from them from the description alone.

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?

'Free.' signals a cost dimension but gives no guidance on when to call this versus base_preflight, base_preview, or base_risk_delta. There are no preconditions or exclusions, so the agent must infer usage from the tool name.

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 readOnly=true and destructive=false, so safety is covered. The description adds two genuinely non-obvious traits: the call is a paid x402 service (a payment/auth prerequisite the agent must handle) and the output is deterministic. It omits cost magnitude, latency, and failure behavior, which keeps it below a 5.

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-loaded with the two most important facts (paid, deterministic report) before the field enumeration. The long comma-separated facet list is dense but earns its place since no output schema exists; it could have been grouped more readably, but there is no filler.

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, the description carries the return-value burden and does so by listing the report's contents, including confidence and limitations. The gaps are the default network when the optional parameter is omitted and the absence of any sibling routing guidance.

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%, with both the address pattern and the CAIP-2 network enum documented in-schema, so the baseline of 3 applies. The description adds nothing about either parameter — notably it never says which network is used when the optional 'network' argument is omitted.

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: a 'deterministic structured report about a Base contract address', then enumerates the exact facets covered (bytecode, verification, proxy, ownership, minting, pause, blacklist, liquidity, etc.). This is far from tautological, but it never distinguishes itself from siblings like base_preview or baseguard_status, which appear to overlap in scope.

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 no statement of when to use this tool, when not to, or which sibling to pick for a lighter or delta-focused check. The only contextual signal is 'Paid x402 service', which tells the agent a cost exists but not when paying it is warranted.

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 cover the safety profile (readOnly, non-destructive, open-world), so the description's added value is cost and fidelity: it is free, and the data is a deliberately 'small real sample' rather than a complete report. That cost/sample-size disclosure is exactly the kind of context annotations cannot carry. It doesn't mention rate limits or how small the sample is.

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 sentences, no waste, with the most decision-relevant fact ('Free.') front-loaded and the usage instruction last. Every clause earns its place.

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, the description usefully enumerates the returned fields, and it explains the cost model and intended use. The remaining gap is the undocumented `network` parameter and its chain enum, the one thing an agent could get wrong when calling.

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%, so the description is the only place parameter meaning could live — yet it only references 'an address' and says nothing about the `network` parameter or that its enum values (eip155:8453 vs eip155:84532) select chains. The agent is left to guess which network is default and whether a testnet address is valid.

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 concrete verb and resource ('Returns a small real sample for an address') and enumerates the exact payload (bytecode size/hash, block number, verification and proxy status), so the agent knows what it gets. The distinction from siblings is only implicit via the 'preview' vs 'full report' framing — none of baseguard_status, base_preflight or base_risk_delta are named, so an agent must infer which to pick.

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?

'Use it to confirm connectivity before paying for a full report' gives an explicit trigger condition and an implied alternative (the paid full report). It stops short of stating when NOT to use it — e.g. for real risk assessment vs. a connectivity probe — and never references the actual sibling tools.

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 cover the read-only/non-destructive/open-world profile, and the description adds genuinely new behavioral facts: the call is paid via x402 and the diff is against a persisted prior snapshot rather than a caller-supplied baseline. It also discloses the return structure (severity + evidence per change). It omits pricing/payment mechanics and first-run behavior.

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 front-loaded elements — pricing model, comparison semantics, then the covered change categories — in a single compact paragraph with no filler. The long enumeration of change types is informative rather than padding.

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, the description usefully sketches the response (per-change severity and evidence, plus intervening events) and covers the paid-service caveat. It leaves significant gaps for an agent: cost/amount, payment flow, and what is returned or raised when no prior snapshot exists for the address.

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 both parameters carry their own descriptions plus an enum on network, so the schema does the heavy lifting. The description adds nothing about the address or the CAIP-2 network choice (e.g., mainnet vs testnet implications), so the baseline 3 applies.

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 (compares) and both operands (previous persisted snapshot vs fresh observation) on a Base contract, then enumerates the change categories and evidence returned. It is clear what the tool does, but it never names or contrasts itself with the siblings base_preflight or base_preview, which an agent must distinguish 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?

Usage is only implied: 'previous persisted snapshot' signals the tool is meaningful only after a snapshot exists, and 'Paid x402 service' signals a cost prerequisite. There is no explicit when-to-use clause, no statement of what happens on a first run with no prior snapshot, and no routing guidance versus the sibling tools.

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