ncrypted

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

The destructiveHint=true annotation already declares that this destroys data, so the description only needs to add context. It does add the precondition that the secret must be unread and a cost note ('Free'), but says nothing about irreversibility, required permissions, or what is returned after the burn.

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 short sentences, front-loaded with the destructive action; nothing is padded. The trailing 'Free' is marketing-ish but does convey cost information an agent might otherwise lack.

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 and only a single annotation, so the description carries most of the burden. It omits the receiptToken's origin, post-burn state, and error behavior for already-read secrets — significant gaps for a destructive one-time-secret operation.

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?

Both required parameters ('id' and 'receiptToken') have 0% schema description coverage and are never mentioned in the description. An agent gets no hint about what a receiptToken is or where to obtain it, so the description fails to compensate for the coverage gap.

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?

Specific verb ('Destroy') plus resource ('a secret you created') and a timing qualifier ('before anyone reads it'), which cleanly separates it from the create/read/status siblings. It stops short of naming those siblings, but the scope 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?

'Before anyone reads it' implies the condition under which burning is appropriate (revoking an as-yet-unread secret), but there is no explicit when-not guidance, no mention of alternatives, and no statement of what happens if the secret has already been read.

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?

No annotations are provided, so the description carries the full burden and does so convincingly: it discloses the 0.005 USDC cost via x402 on Base, the client capability requirement, the one-time self-destruct semantics, and the hosted-mode trust model (plaintext visible briefly over TLS, never stored or logged) with a zero-knowledge alternative. These are exactly the side effects and prerequisites an agent needs before invoking.

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 what the tool does, then cost/requirement, then the security caveat and alternative — every sentence carries distinct, actionable information with no filler. The length is justified by the payment and trust-model disclosures.

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 implies but never states the return value (the one-time link/URL and any expiry metadata), which an agent would benefit from knowing. Everything else an agent needs — cost, prerequisite, destruction semantics, privacy model — is covered.

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 all three parameters are documented in-schema (secret with 64 KB cap, optional passphrase as second factor, ttl_seconds range/default), so the baseline is 3. The description adds no parameter-level detail beyond what the schema already supplies.

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 precise verb and resource ('Store a password, API key or sensitive note as a one-time link'), plus the defining behavior (self-destructs after a single read). This is clearly separable from siblings ncrypted_read, ncrypted_burn and ncrypted_status — this is the only one that creates/stores.

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 concrete usage context: share the link with a person or another agent, never echo the secret in chat, and notes the paid-path prerequisite (MCP client must support x402). It names an alternative, but that alternative is a different deployment (local zero-knowledge server) rather than a routing choice among sibling tools, so no explicit when-not-to-use-this-tool guidance.

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 declare destructiveHint=true and idempotentHint=false, but the description goes well beyond them: it explains that reading permanently destroys the secret, that hosted mode exposes plaintext briefly over TLS, that nothing is stored or logged, and offers a zero-knowledge alternative. That is exactly the added 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?

Front-loads the action and the destructive consequence, then layers privacy caveats. Slightly dense with the hosting/encryption discussion, but every sentence carries information an agent needs before calling a one-time-read tool.

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 two-parameter tool with no output schema, the description covers the return value ('return the secret'), irreversibility, failure/security considerations, and the alternative deployment. Nothing an agent needs to call it 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 both link and passphrase are already documented, including the #key fragment requirement. The description reinforces the link format with a concrete template but adds no new semantics for passphrase, so 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 (open/read) and resource (one-time secret link) and says exactly what is returned. The URL template (https://.../s/{id}#{key}) makes the target unambiguous, and the tool's role is clearly distinct from ncrypted_create or ncrypted_status.

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 explicit operating guidance ('Only use the value for the task at hand and do not repeat it in chat') and tells the agent when to prefer the local server for zero-knowledge decryption. It never explicitly contrasts with sibling ncrypted_burn, so the routing between read and burn is left to inference.

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?

readOnlyHint=true is consistent with a status check, so no contradiction. The description does add real value beyond the annotation by enumerating the four possible lifecycle states and noting the call is free, but it says nothing about how the receiptToken is validated or any rate/abuse limits on the lookup endpoint.

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?

One compact sentence that front-loads the core action, with the state list inline and the cost hint ('Free') at the end. Nothing is wasted, though the trailing fragment could have been folded in more smoothly.

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 two-parameter read-only tool with no output schema, the description covers the conceptual return values (the status set) adequately, but omits any explanation of the required receiptToken and how to obtain it, which is the main gap 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?

Schema coverage is 0% and neither property has a description. The description only loosely implies what 'id' is ('a secret you created'); the required 'receiptToken' — a security credential — is never mentioned or explained, so the description does not compensate for the coverage gap.

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 ('Check') and resource ('whether a secret you created has been read yet') and enumerates the possible states (pending, read, burned, expired), which clearly separates it from ncrypted_read (fetch content) and ncrypted_burn (destroy). It never names those siblings explicitly, so differentiation is inferential rather than stated.

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 phrase 'a secret you created' implies the caller must be the creator, and 'Free' hints it is the cheap option for polling before a read, but there is no explicit when-to-use / when-not-to-use guidance or named alternative such as ncrypted_read.

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