Prism MCP

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, so the safety profile is fully covered by structured data. The description adds one genuinely new behavioral fact — that the call is free — plus a note that the content explains how to verify claims, but says nothing about freshness, caching, or result size.

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 compact sentences, front-loaded with what is returned, followed by cost/arity and a concrete empty-argument example. Nothing is padded, though the example adds marginal value for a tool with no inputs.

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?

An output schema exists, so return-value detail is not required, and the description covers what the payload concerns and the call cost. For a zero-argument informational tool this is nearly sufficient, with only the vague 'how to check each claim' left unclarified.

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?

With zero parameters and 100% schema coverage, the baseline is 4. The description reinforces this with 'no arguments' and an empty-object example, which is consistent and helpful for an agent constructing the call.

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 (returns) and a specific resource (who runs Prism, the operating theory, working practices, and claim verification), which is clearly distinct from the audit_*, notes_*, and RPC-oriented siblings. It stops short of naming or contrasting any sibling explicitly, so it does not reach a 5.

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, no arguments' hints at a low-cost, always-safe call, but there is no explicit statement of when an agent should reach for this tool versus the audit or notes tools. No prerequisites, exclusions, or alternatives are given.

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 the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true). The description adds genuinely useful behavioral context beyond that: which key to sign with (EIP-191 personal_sign) and, importantly, that time burns only while a call runs whereas an open websocket subscription burns continuously. It does not cover failure/rejection behavior or rate limits, so it is solid but not rich.

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 in total length but written as a single run-on block of telegraphic fragments ('op: open {channelId} takes the channelId buy_time returned and answers {nonce, sign}') with no line breaks or grouping, forcing the reader to reparse. The trailing JSON example earns its place, but the structure does not front-load the lifecycle clearly.

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?

This is a complex six-op state machine, and the description covers the open→prove→use→close sequence plus billing semantics. With annotations present and an output schema available for return values, the definition is close to self-sufficient; only error/edge-case behavior is missing.

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%, so the baseline would be 3. The description goes beyond the schema by binding each optional parameter to specific op values (nonce/signature to prove, credential to on/off/status/close) and by specifying the signing standard (EIP-191, personal_sign) for the signature parameter, which the schema does not state.

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 opening sentence states the resource (a line/channel) and the lifecycle behavior ('calls on it spend bought time and carry no payment'), and the op list names the concrete operations. It is distinguishable from siblings like buy_time and call_rpc, though the dense telegraphic phrasing makes the core purpose harder to extract than it needs to be.

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 lays out the flow: open takes the channelId that buy_time returned, prove consumes open's {channelId, nonce, signature}, and on/off/status/close consume the credential. That sequence gives real when-to-use context and implicitly points at buy_time as a prerequisite, but it never states when not to use the tool or what happens on misordering.

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 only declare readOnly=false/openWorld=true/non-idempotent/non-destructive; the description goes well beyond them by disclosing immutability (nobody can edit or delete, 'us included'), free gas sponsorship, the 4096-byte cap, the 60-calls/hour-per-address limit, and the gas-exhaustion fallback behavior. This is exactly the behavioral context annotations cannot carry.

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?

Information-dense with no filler: cost, immutability, signing routing, anonymity fallback, size cap, gas fallback, rate limit, and example all appear in sequence, with the core verb first. Every sentence carries a distinct operational fact.

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 an output schema present, return format needn't be described, and the description still covers auth (signature path), limits, failure behavior, and constraints. Nothing an agent needs to call this correctly is missing.

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, but the description adds real value: it states the salt/address/signature are only meaningful together with a signature and provides a concrete example payload showing how the four fields compose. That exceeds what the schema alone conveys.

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 ('Write a note on an immutable notepad') and immediately distinguishes itself from the sibling notes_read and notes_sign. An agent can tell this is the write path versus the read/sign paths without opening any schema.

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?

Explicitly routes the agent: sign first with notes_sign to post under a wallet name, otherwise the note posts anonymously. It also names the fallback condition (daily gas spent) and the rate limit, so the agent knows when this call succeeds versus returns a transaction to send itself.

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 (readOnlyHint, idempotentHint, non-destructive), but the description adds non-redundant context: the call is free, rate-limited to 60 calls/hour per network address per tool, and posts under wallet-name attribution if used. It does not explain failure or error behavior, but the disclosure is strong beyond the 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?

Dense but front-loaded: purpose first, then workflow, then rate limit, then a concrete example. Every sentence carries information, though the run-on workflow sentence could be split for scanability.

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 an output schema present, the description needn't spell out return values, and it correctly focuses on workflow, cost, rate limit and the anonymous alternative. An agent has everything needed to call notes_sign and route its output correctly.

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 body/salt semantics are already documented; the baseline would be 3. The description adds workflow meaning by tying the body and returned salt to the notes_post call, implying the salt must be reused with the identical body — value beyond the 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 states the tool returns signing data so a note posts under your wallet's name, which is a specific purpose distinguishable from notes_post (which submits) and notes_read. The verb is slightly implicit ('The data to sign') rather than a crisp action verb, but the intent 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?

It gives explicit workflow routing: sign the returned typed_data with eth_signTypedData_v4, then pass the same body, address, signature and salt to notes_post. It also names the alternative path ('Skip it to post anonymously'), so the when-to-use decision is fully specified.

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