webhook-inbox

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

Beyond the annotations, the description discloses authentication requirements ('No API key'), cost ('No debit'), persistence ('Stores raw body + headers'), error conditions ('Rejects revoked... or expired... 410'), and constraints ('Body limit 1MB'). These are exactly the behavioral details an agent needs and are not available from the annotations alone.

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 compact and front-loaded: the first sentence establishes the core operation, and each subsequent sentence adds a distinct fact (cost, persistence, error behavior, limits). There is no filler or redundant restatement of the tool name.

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 simple capture tool with no output schema, the description covers the critical operational aspects: endpoint, auth, cost, storage behavior, rejection cases, and body size limit. It could mention the success response or how to format the body in more detail, but the schema already handles body formatting and the description is otherwise sufficient 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 schema already describes all three parameters, so the baseline is 3. The description adds meaningful context by specifying the endpoint shape for id, the 1MB cap relevant to body, and clarifying that this capture call has no API key requirement. This goes beyond a simple restatement of schema fields.

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 clear action ('Capture a raw POST'), the exact endpoint ('POST /c/{id}'), and the data stored ('raw body + headers'). It also differentiates from siblings by explicitly noting it is not an install entry and that stored data feeds list_inbox_events, so there is no ambiguity about the tool's role.

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 gives strong contextual signals: it is public, requires no API key, and incurs no debit, which tells the agent when this tool is appropriate. It does not explicitly name alternative capture or event tools, but the references to list_inbox_events and the schema's id-from-mint_inbox hint make the workflow context clear.

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?

The description discloses important behavioral traits beyond annotations: this is a TEST-mode operation, returns only credits_pending, credits remain non-spendable until confirm_credits succeeds, and a caller key is required. This is valuable context that annotations alone do not provide.

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 tightly packed sentences deliver the core purpose, the critical pending-state caveat, and the auth requirement. No filler or redundancy.

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 one required parameter, clear behavioral caveats, and no output schema, the description covers everything an agent needs to invoke it correctly: what it does, what it returns, what it does not do, and what credential is needed.

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% and the only parameter, pack_id, is already described as coming from list_credit_packs. The tool description adds little beyond 'for a pack,' so it does not meaningfully enhance the parameter semantics.

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 and resource: creates a Stripe TEST PaymentIntent for a credit pack via POST /credits/checkout. It clearly differentiates itself from confirm_credits by explaining this is intent-only and does not grant spendable credits.

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 makes the usage context clear: call this to initiate a checkout intent, not to actually grant credits. It names confirm_credits as the follow-up step, effectively routing the agent appropriately, though it could be even more explicit about when to prefer alternatives.

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 indicate readOnlyHint=false (mutation) and destructiveHint=false. The description adds context by explaining that the tool 'appends credit.purchase with credits_added' and that credits become spendable, which is a behavioral disclosure beyond the annotations. It does not mention error conditions or idempotency, but for a test tool this is adequate.

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 two sentences with no filler. The primary action and endpoint are front-loaded, followed by the effect and test-only constraint. Every word contributes to understanding the tool's purpose and scope.

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 single-parameter test tool with no output schema, the description covers purpose, effect, and test scope. It does not describe response behavior or idempotency, but given the simplicity and existing annotations, the information provided is sufficient 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 schema covers the single parameter with a clear description ('PaymentIntent id (pi_…) from checkout_credits'), so schema coverage is 100%. The description adds minimal extra meaning by referencing the card and endpoint, but does not elaborate on parameter format or sourcing beyond what the schema already states.

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 clearly states the verb ('Confirm'), the resource ('a TEST PaymentIntent'), and the specific effect ('credits become granted/spendable'). It also includes the endpoint and the test card used, and specifies it is TEST only, distinguishing it from production operations and other tools like checkout_credits.

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 implies usage after checkout_credits by referencing 'PaymentIntent id (pi_…) from checkout_credits' in the schema, and states 'TEST only'. It does not explicitly say 'use this after checkout' or provide exclusions, but the context is clear enough for an agent to infer the intended workflow.

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 destructiveHint=false, covering the safety profile. The description adds a little context by noting the balance is 'derived' and scoped to the caller_id, but it does not disclose rate limits, authentication requirements, or other behavioral traits beyond what annotations provide.

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, focused sentence that front-loads the core concept ('Derived prepaid balance') and adds only the endpoint and scope. No wasted words.

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 parameterless, read-only tool with annotations covering safety, the description provides the essential information: what it returns (a balance) and for whom (caller_id). It could add a bit more about the meaning of 'derived' or the response format, but given the tool's simplicity, it is largely complete.

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 the schema already fully covers parameter semantics. The description usefully clarifies that the balance is implicitly for the caller_id (likely from authentication), which is the only meaningful input context even though it is not a formal parameter.

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 identifies the resource precisely ('Derived prepaid balance for this caller_id') and includes the GET endpoint, making the operation clear as a retrieval. However, it lacks an explicit verb (e.g., 'get' or 'retrieve') and does not explicitly differentiate from sibling tools, though the resource is distinct enough.

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?

No guidance is given about when to use this tool versus alternatives like credit_events or checkout_credits. The phrase 'for this caller_id' implies a current authenticated context, but there is no explicit context, exclusion, or alternative indication.

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 destructiveHint=false, covering the safety profile. The description adds the append-only ledger nature and event types, which is useful, but does not disclose pagination, ordering, or response format. This is some added value but not rich behavioral context.

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, dense sentence that front-loads the core scope ('Append-only Ledger events for this caller_id'). It is efficient and contains no wasted words, but the heavy use of jargon ('first_key', 'reason=inbox_mint') makes it less approachable for an agent.

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 simple no-parameter read-only tool, the description covers the event categories and endpoint, which is adequate. However, without an output schema, missing details about response format, pagination, or ordering could leave an agent uncertain about what to expect. The description is sufficient but not fully complete.

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 and the schema is effectively complete. The description's mention of event types is extra informational context, not parameter semantics. With 0 parameters, the baseline is 4, and the description does not need to compensate.

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 clearly identifies the resource (credit ledger events) and the endpoint (GET /credits/events), enumerating specific event types. It distinguishes from siblings like credit_balance and list_inbox_events by focusing on the credit ledger. However, it lacks an explicit action verb such as 'list' or 'retrieve', which slightly reduces clarity.

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 implies usage by naming the event types and endpoint, but does not explicitly state when to use this tool versus alternatives like list_inbox_events or credit_balance. No exclusions or sibling comparisons are provided, leaving the agent to infer the right context.

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 destructiveHint=false, and the description adds meaningful behavioral context: it specifies the HTTP method (GET), public access ('No key'), and the exact readiness fields reported ('billing (test|live|gated) and runner_ready'). This goes beyond what annotations alone provide without contradicting them.

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, information-dense sentence. It front-loads the most important fact ('Public readiness'), then the endpoint, then the fields, and finally the auth requirement ('No key'). Every word earns its place with no fluff.

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 health check, the description is complete: it states the HTTP method, public access, and what the response reports. There is no output schema, but the description names the response fields, so an agent knows what to expect. Given the low complexity, nothing essential 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?

The tool has zero parameters, so the baseline is 4. The description mentions no parameters, which is accurate given the empty schema. No additional parameter explanation is needed.

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 clearly identifies the tool as a public readiness/health check: 'Public readiness (GET /health)' and lists the reported fields, 'billing (test|live|gated) and runner_ready'. This distinguishes it from the sibling tools, which are all about inboxes, credits, and keys, by making the health-check scope explicit.

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 makes the usage context clear by labeling the tool as 'Public readiness' and noting 'No key', implying it is for unauthenticated health/readiness checks. It does not explicitly state when not to use it or name alternatives, but the sibling set is so divergent that exclusion guidance is less necessary.

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?

With no meaningful annotation detail beyond non-read-only and non-destructive, the description carries the behavioral burden well. It discloses that the secret 'whi_…' is returned only once, that the first issue grants a free credit with reason 'first_key', and that X-API-Key is an alias for Bearer auth. These are exactly the kind of non-obvious behaviors an agent needs.

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 compact and front-loaded with the core action. Most sentences add relevant context such as one-time secret exposure and free credit. A minor deduction: the 'Quote cost with quote_credits before mint_inbox' sentence is somewhat tangential to issuing a key and could distract from the tool's immediate purpose.

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 tool with no output schema, the description covers the essential operational details: endpoint, installation context, one-time secret, auth preference, and credit behavior. It does not describe possible errors or response format, but that is less critical given the tool's simplicity and the absence of parameters.

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 parameterscars, so there is no parameter schema for the description to supplement. The baseline of 4 applies because no parameter documentation is needed, and the description still clarifies the endpoint and auth expectations.

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 opens with a clear verb and resource: 'Mint a caller key (POST /keys).' This directly states the action and endpoint. It is also differentiated from siblings like revoke_key, rotate_key, and verify_key by framing this tool as the initial issuance action.

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 provides clear context for when this tool is used: at bot install, after discovering the sole advertised entry, and as the first key issuance. It also gives practical guidance like preferring Authorization: Bearer and quoting cost before mint_inbox)Skip. However, it does not explicitly state when not to use this tool versus alternatives.

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 destructiveHint=false. The description adds useful behavioral context beyond that: the packs are TEST-only, the operation is a GET, and actual credits are only granted after confirm_credits. No contradiction with 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?

Two short sentences, front-loaded with the core purpose and endpoint. The second sentence earns its place by clarifying that checkout_credits alone does not grant credits, which helps an agent avoid a common misuse. No filler or repetition.

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 listing tool with no output schema, the description covers the essential information: resource, test nature, endpoint, and surrounding credit flow. It does not describe what a credit pack contains or whether the list is paginated, but that burden is low for such a simple 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?

The input schema has zero parameters, so the baseline is 4. There is nothing to document beyond what the schema already shows; the endpoint mention is sufficient and no parameter-level detail is needed.

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 title and description clearly state the operation: listing credit packs. The description adds specificity with 'Prepaid TEST packs' and the explicit GET endpoint (/credits/packs), so the resource and scope are unambiguous. It also references checkout_credits and confirm_credits, which helps an agent place this tool within the broader credit-purchase flow.

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 explicit guidance on when to use list_credit_packs versus alternatives such as credit_balance or quote_credits. The sentence about checkout_credits being intent-only clarifies a related flow but does not tell the agent when choosing this tool is appropriate or inappropriate.

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 destructiveHint=false. The description adds value by stating 'Does not debit', disclosing owner-only visibility ('Other callers see 404'), and specifying the response format (JSON headers + body).

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?

Four short sentences, each adding distinct information: operation, output format, side-effect guarantee, and authorization behavior. No filler or redundancy.

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 simple one-parameter read-only tool with no output schema, the description covers the endpoint, return content, side-effect behavior, and access control. Nothing essential is missing for an agent to call it 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% and the single parameter 'id' is already well described as 'Inbox id from mint_inbox (inb_…)'. The description does not add parameter-level detail, but the schema carries the full burden, so baseline 3 is appropriate.

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 and resource: 'List captured POSTs' and 'GET /inbox/{id}/events', and clarifies the output as 'JSON (headers + body)'. It clearly distinguishes this from siblings like capture_inbox, mint_inbox, and credit_events by scoping it to inbox event history.

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 gives clear context: this is the owner-only list operation, and non-owners receive a 404. It implies when to use it, but it does not explicitly name alternative sibling tools or state when not to use them.

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 convey readOnlyHint=false and destructiveHint=false. The description adds substantial behavioral detail beyond this: debits 1 credit on success with the exact reason code, 201 response body fields, the error envelope (code/message/retryable/next), and specific 401/402 response semantics. This fully discloses side effects and failure modes.

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 core purpose is front-loaded in the first sentence, and every clause is information-dense. However, the remaining content is a run-on wall of technical detail (auth, credits, error handling) with no logical separation, making it harder to parse than a structured presentation would be.

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?

Despite having no output schema, the description fully documents the 201 response fields (id, capture_url, expires_at, credits_remaining), the error envelope, credit debit behavior, and authentication requirements. For a 0-parameter tool with this credit/error complexity, nothing an agent needs to call or interpret the result 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?

The tool has 0 parameters and 100% schema coverage, so the baseline is 4. The description adds no parameter meaning (there are none), but documents auth header expectations and response fields that enrich the call context without contradicting the 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 states a specific verb and resource: 'Mint a capture URL (POST /inbox).' This clearly differentiates from sibling capture_inbox (which presumably targets an existing inbox), and the title 'webhook inbox, request bin' reinforces the purpose. An agent can tell exactly what operation this performs.

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?

Provides clear workflow context: quote first with quote_credits (no debit), install via GET llms.txt only, prefer Bearer auth with X-API-Key as an alias. It even routes to a sibling tool for a prerequisite step. It lacks explicit when-not-to-use guidance for capture_inbox, but the procedural context is strong.

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 mark readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'without debit' and 'dry-run'. It also adds useful behavioral details about the response, naming cost, balance, and would_succeed.

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 one dense, well-structured sentence that front-loads the core behavior and includes the endpoint plus response fields. No wasted words.

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 low-complexity tool with one optional parameter and no output schema, the description is complete enough. It explains what the operation does, what it returns, and how it differs from debit operations, while annotations cover safety.

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% and the only parameter, op, is already documented with its default. The description repeats 'op=inbox' but adds no new semantic information about allowed values or behavior 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 a specific action ('dry-run cost'), the resource ('credit cost'), the endpoint, and the key differentiator ('without debit'). This clearly distinguishes quote_credits from debit-related siblings like checkout_credits and confirm_credits.

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 'dry-run cost for an op without debit' provides clear context that this is a preview or estimation tool rather than an executing one. It does not name an alternative explicitly, but the no-debit framing makes the appropriate usage evident.

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 flag destructive behavior, and the description goes further by specifying the exact side effect ('Does not refund the mint debit') and the authorization model. There is no contradiction with readOnlyHint=false or destructiveHint=true.

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 short sentences, each carrying a distinct piece of information: action, side effect, and permission. No filler or redundant restatement of the schema.

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 one-parameter delete-style tool, the description supplies the action, HTTP method, authorization, and financial consequence. The absence of an output schema does not create a critical gap because the behavior and prerequisite are fully stated.

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%, with the single 'id' parameter documented as coming from mint_inbox (inb_…). The description adds no additional parameter semantics, 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?

The description defines a specific verb ('Stop') and resource ('inbox'), and adds the HTTP route 'DELETE /inbox/{id}' to make the operation unambiguous. It clearly differentiates from sibling tools like capture_inbox or mint_inbox by focusing on ceasing captures.

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 implies the trigger: use it when captures should no longer be accepted, and clearly states the permission constraint 'Owner only'. It does not explicitly name sibling alternatives or exclusion conditions, but the context is clear enough for correct selection.

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?

The description reveals the concrete outcome (old secret returns 401 invalid_api_key) and notes that the same id is revoked, which is useful behavioral context beyond the destructiveHint annotation. It also clarifies the acceptable auth header and that no ops files are edited, though it does not discuss side effects 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?

Three compact sentences, each carrying distinct information: the core action, the idempotent outcome, and the invocation preference. No filler or redundancy.

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 parameterless destructive tool, the description covers the action, the HTTP endpoint, the failure mode, and the required auth mechanism. No output schema exists, and the annotations already signal destructiveness, so the description is sufficient for an agent to call this tool 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?

The input schema has zero parameters, and the description adds meaning by explaining how the secret is presented (via Authorization header) rather than a schema property. Baseline for zero parameters is 4, and the description does not need to document any parameters.

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 opens with 'Invalidate the presented secret', a specific verb and resource, and the title adds 'caller key' to disambiguate from revoke_inbox. It also names the HTTP endpoint, making the action unambiguous even among sibling 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?

The description gives transport-level guidance (prefer Bearer, X-API-Key alias) and an exclusion ('No ops file-edit'), but does not explicitly state when to choose this tool over rotate_key or revoke_inbox. Usage context is implied by the destructive nature of invalidation, but no alternative tools are named.

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?

Discloses crucial runtime behavior beyond annotations: the new whi_… key is returned only once, the old key subsequently fails with 401 invalid_api_key, and id/caller_id and credits are preserved. This is rich, non-obvious context an agent needs.

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 dense sentences, each earning its place: what happens, what is returned, and how to authenticate. Front-loaded with the core operation and 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?

Despite no output schema, the description covers the response (new key returned once), the failure mode (401), side effects (old key invalid), and invariants (same id/credits). Nothing essential is missing for an agent to call this 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?

There are no parameters, so the schema carries no burden. The description clarifies that the secret is 'presented' via Authorization, which is genuinely useful context for invoking the tool despite the 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 clearly states a specific action ('Replace the presented secret') and resource ('caller key'), with the endpoint and behavior spelled out. It differentiates from siblings like revoke_key and issue_key by emphasizing that identity and credits are preserved while the secret changes.

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?

Provides concrete usage context: use Authorization: Bearer, X-API-Key is only an alias, and no ops file-edit is needed. It does not explicitly name alternatives or say 'use this instead of revoke_key', so it stops short of a full 5.

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 destructiveHint=false, covering the safety profile. The description adds valuable behavioral context: it states that the request confirms the key, notes that X-API-Key is only an alias, and explicitly says it does not echo the secret.

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 three short sentences with no filler. It leads with the action and endpoint, then clarifies credential aliases and a key security behavior, making every sentence useful.

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 verification tool with annotations covering safety, the description is complete enough for an agent to invoke it correctly. It specifies the endpoint, acceptable credentials, and the important non-echo behavior; no return format is required for such a simple confirmation endpoint.

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 input schema has zero parameters, so the baseline is 4. The description nonetheless adds relevant invocation details by naming the accepted authentication mechanisms, though it does not need to describe parameters that do not exist.

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 uses the specific verb 'Confirm' and identifies the exact resource: the caller key via GET /keys/verify. It also clarifies accepted credential forms, distinguishing this from sibling key-management tools like issue_key, revoke_key, and rotate_key.

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 clearly places this tool as a key-verification endpoint for the webhook inbox/request bin context. It does not explicitly list exclusions or conditions favoring alternatives, but the intended usage is clear and unambiguous.

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