Skip to main content
Glama

fresh402_contract_watch

Observe code, standard proxy slots, common getters, explicitly selected storage/ABI and bounded selected events at one finalized Base address; optionally compare an owned prior snapshot. Selected single-provider evidence only; unknown controls remain unknown. Commercial input binds to the original x402/MPP/prepaid request and REQUIRED random32-byte private recovery token for x402/MPP. REST sends X-Fresh402-Recovery-Token; MCP sends params._meta['fresh402/recovery-token']. Persist the secret with the original proof/input before authorizing. No client request_id; recovery reuses the original result with no new RPC or debit. Provider failure/partial scan never becomes a paid success. A confirmed paid response with observation_saved=false and persistence_error is pending domain finalization: keep original proof/input/token, retry recovery only, and do not use returned snapshot/cursor IDs until saved flags become true. $0.010000 USDC on Base per call; use an approved compatible payment client. Prepaid requires eligible finalized all-service credits or an original explicit service-specific tariff4 grant; inspect authenticated /v3/prepaid/quote/contract_watch. Historical web package terms remain unchanged. Records retain30days; original private financial recovery retains7days. Server-side provider approval and published tariff gates apply; paying agents do not need their own RPC credentials or an operator-created grant when eligible all-service credits are available. Read /v3/prepaid/all-services and accept its exact terms before a new all-service purchase. Optional free evaluation: inspect GET /v3/agent-trial for the CAPTCHA-free machine trial (unfunded EOA ownership signing required). Web tools may also use the separate human trial at /v2/trial. Only enabled, eligible allowances authorize free execution; shared capacity can return 429 earlier. Send X-Fresh402-Trial-Key and a distinct persisted Idempotency-Key per logical REST or MCP call. Reuse the same tool/input/key for retained recovery. Never mix trial and payment/prepaid credentials. Exhaustion never authorizes a charge; ordinary requests without trial credentials retain the paid challenge.

Input Schema

NameRequiredDescriptionDefault
blockNoFinalized only. Every state read pins the selected block hash with requireCanonical:true; no latest/number fallback.finalized
readsNoAt most one unverified zero-argument view/pure ABI read with one supported static output.
slotsNoAt most one exact bytes32 storage slot; no inferred layout.
addressYes20-byte Ethereum address; lowercase/uppercase accepted, mixed case must have a valid EIP-55 checksum. Normalized to checksummed form.
chain_idYesBase mainnet only; returned provider chain must match.
event_topicsNoAt most one exact topic0 at this contract, bounded to the existing lookback/call limit. Dense or excessive work fails the whole paid operation; no partial success.
events_from_blockNoOptional first event block; otherwise previous snapshot block+1, or current block initially. Older than 32 blocks returns lookback_gap, without skipping to recent history.
previous_snapshotNoOptional owned snapshot_id from a successful saved contract_watch result, retained for30days. Same payer or prepaid account, chain, address and provider required. Foreign/missing IDs return404; expired IDs return410 without silently starting a new baseline.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose key traits: $0.01 USDC cost, required recovery-token handling, no partial success on provider failure, pending-finalization semantics for saved observations, retention windows, and 429 capacity behavior. It is dense and occasionally muddled, but behaviorally informative.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first sentence, but the remainder is a long wall of payment, prepaid, trial, and recovery boilerplate. Much of it is relevant to a paid tool, yet repetition and density hurt readability; a structured split into operation vs. payment semantics would be clearer.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex paid tool with no annotations and no output schema, the description covers payment authorization, recovery tokens, trial credentials, retry behavior, and retention rules thoroughly. It stops short of describing the actual response shape, but the operational context an agent needs to invoke it correctly is largely present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter is already well documented in the schema (e.g., slot and event_topics constraints, previous_snapshot ownership rules). The description adds only general framing ('explicitly selected storage/ABI', 'bounded selected events') without new syntax or format detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence names a specific verb ('Observe') and enumerates concrete resources (code, proxy slots, getters, selected storage/ABI, bounded events) at a finalized Base address, plus optional snapshot comparison. An agent can tell this is a contract-inspection tool, though the description does not explicitly differentiate it from siblings like fresh402_token_facts or fresh402_smart_diff.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives extensive operational context about payment, recovery, and trial usage, but never states when to choose this tool over contract_diff, token_facts, or wallet_watch. Usage is implied by the observation scope rather than routed explicitly.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources