actionlayer
Server Details
Concierge for AI agents: takes action in the physical world — book, order, register, resolve.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4/5 across 14 of 14 tools scored. Lowest: 2.6/5.
Each tool targets a distinct operation or resource. The clear separation between single-action tickets and multi-step jobs, along with specific verbs (create, get, cancel, resume, submit), prevents confusion. Even similar tools like cancel vs cancel_job are distinguished by descriptions.
All tool names follow the consistent pattern 'actionlayer_verb_noun', with verbs like get, create, cancel, invoke, list, provide, reply, start, submit. The naming is predictable and uniform, despite occasional compound objects (action_ticket).
14 tools cover both single-action tickets and multi-step jobs, including lifecycle operations, credential management, feedback, and exploration (list tools). The count is well-scoped for the domain without unnecessary bloat or gaps.
The tool set covers the main workflows: creation, polling, cancellation, resumption, credential submission, and feedback. However, it lacks tools for listing all tickets/jobs or updating them, which are minor gaps. Core operations are complete.
Available Tools
14 toolsactionlayer_cancelAInspect
Cancel a non-terminal ticket (single-action task; tkt_*).
Idempotent on terminal states. For multi-step plans
(job_*), use actionlayer_cancel_job instead.
| Name | Required | Description | Default |
|---|---|---|---|
| ticket_id | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must fully disclose behavior. It mentions idempotency on terminal states and ticket type, but does not describe the cancellation effect (e.g., changes to ticket state, side effects, or destructive nature). Some transparency, but gaps exist.
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, directly addressing purpose, behavior, and alternatives without extraneous words. Highly efficient.
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 tool with an output schema (not shown), the description covers core aspects: cancellation target, idempotency, and alternative. It does not specify what 'non-terminal' means or authorization requirements, but is fairly complete given complexity.
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 has 0% description coverage for the sole parameter `ticket_id`. The description implies the parameter is a ticket ID but provides no additional details (format, constraints, examples) beyond the schema's type 'string'.
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 explicitly states the action ('Cancel'), the resource ('non-terminal ticket with `tkt_*`'), and distinguishes itself from the sibling `actionlayer_cancel_job` for multi-step plans.
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 indicates when to use this tool (for single-action tickets) and when not to (for multi-step plans, directing to `actionlayer_cancel_job`). It also notes idempotency on terminal states, guiding safe usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_cancel_jobAInspect
Cancel an in-flight job (multi-step plan; job_*).
Idempotent on terminal states. For single-action tasks
(tkt_*), use actionlayer_cancel instead.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Mentions idempotent on terminal states, which is key for a cancel operation. No annotations provided, so description carries burden; could elaborate on side effects or auth requirements but 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?
Two sentences, front-loaded with core action and context. 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?
Covers purpose, usage guidance, and key behavioral trait. Output schema exists so return values not needed. Lacks mention of prerequisites or result handling, but sufficient for the tool's simplicity.
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?
Single parameter job_id is a string, no extra description beyond schema. Schema coverage is 0%, but parameter is simple and self-explanatory; no additional format or source guidance given.
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?
Description clearly states it cancels an in-flight job for multi-step plans (job_*), distinguishing from single-action tasks.
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 tells when to use this tool (for job_* plans) and when not to (use actionlayer_cancel for tkt_* tasks). Also notes idempotency on terminal states.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_create_jobAInspect
Create a multi-step job from a natural-language goal. The planner decomposes it into ordered actions with output piping.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | ||
| deadline | No | ||
| budget_usd | No | ||
| webhook_url | No |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full burden. It discloses the job creation and decomposition behavior but omits async nature, idempotency, or side effects. The existing output schema context partially compensates.
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 concise sentences with no unnecessary words, front-loading the core 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?
Despite having an output schema, the description is too minimal. It does not cover optional parameters, return format, error conditions, or prerequisite context for a tool with 4 parameters and no annotations.
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%, yet the description only explains the 'goal' parameter as a natural-language goal. It does not clarify 'deadline', 'budget_usd', or 'webhook_url', leaving their semantics unclear.
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 tool creates a multi-step job from a natural-language goal, distinguishing it from siblings like actionlayer_cancel_job or actionlayer_get_job by specifying the unique input and process (planner decomposition).
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 use when a natural-language goal needs decomposition, but it does not explicitly state when not to use it or compare against alternatives like actionlayer_invoke_action for single actions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_get_action_ticketBInspect
Poll an action ticket's current state. Stop polling when is_terminal=true.
| Name | Required | Description | Default |
|---|---|---|---|
| ticket_id | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions polling and terminal condition but lacks details on rate limits, authentication, or what 'current state' entails. The behavior is partially disclosed.
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 redundancy. It front-loads the core action (poll) and adds a critical stop condition. Could be slightly more verbose to improve clarity.
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?
Given the presence of an output schema, return values need not be explained, but the description lacks context for when this tool fits in a workflow (e.g., after invoking an action). No prerequisites or relationships to siblings are mentioned.
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 the description does not explain the ticket_id parameter beyond implying it identifies the ticket. No format or source info is given, failing to compensate for low schema coverage.
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 tool polls an action ticket's current state and specifies the stop condition (is_terminal=true). It distinguishes from siblings like actionlayer_get_job by focusing on action tickets.
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 for polling, but does not explicitly state when to use this tool versus alternatives like actionlayer_cancel or actionlayer_resume_job. No guidance on when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_get_jobAInspect
Read a job's current state + per-step items.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It indicates a read operation but does not disclose idempotency, authentication needs, or any potential side effects. Minimal transparency is provided beyond the basic action.
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 extremely concise at 8 words, front-loaded with the key action and resource. No waste.
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?
Given the presence of an output schema, the tool is largely complete for its purpose. However, it could provide more context on what 'per-step items' entails or the possible states.
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%, yet the description does not explain the job_id parameter beyond its name. It fails to add meaningful context about how to obtain or use the 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 clearly states the tool reads a job's current state and per-step items, using a specific verb and resource. This distinguishes it from sibling tools like actionlayer_cancel_job or actionlayer_create_job.
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 provided on when to use this tool versus alternatives like actionlayer_get_task or actionlayer_list_actions. The description lacks context for selecting the appropriate tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_get_taskAInspect
Read the current state of a ticket. Poll until state is one of: completed, failed, cancelled, blocked_on_user.
| Name | Required | Description | Default |
|---|---|---|---|
| ticket_id | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It correctly implies a non-mutating read operation ('Read') and describes the polling behavior. However, it does not explicitly state that it is safe/read-only or disclose any potential side effects or required permissions.
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, concise sentence that conveys both the operation and the expected usage pattern (polling). There is no wasted text, and it is appropriately front-loaded with the core action.
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?
Given the simple input (one required parameter) and the presence of an output schema (which documents the return), the description is largely complete. It covers the tool's purpose, the resource, and the recommended polling approach. Minor gaps include lack of parameter documentation and explicit safety guarantees.
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 coverage is 0%, meaning the description adds no explanation for the 'ticket_id' parameter. Although its purpose is somewhat inferable from context, the description should explicitly state that ticket_id identifies the ticket whose state is being read. This is a minimal addition that would significantly aid an AI agent.
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 tool reads the current state of a ticket and specifies the target states for polling. The verb 'read' and resource 'ticket' are specific, and it distinguishes from sibling tools (e.g., actionlayer_cancel, actionlayer_start_task) which perform different actions.
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 explicitly instructs to poll until a specific state is reached, providing clear context on how to use the tool repeatedly. However, it does not explicitly state when not to use it or mention alternative tools for similar tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_invoke_actionAInspect
Invoke a single action with typed inputs.
inputs must match the action's input_schema EXACTLY
(additionalProperties is rejected). Task-level orchestration
metadata — idempotency_key, max_budget_usd, webhook_url,
deadline — does NOT belong in inputs; that envelope lives
on actionlayer_start_task. If you need those, call
actionlayer_start_task instead.
API actions run synchronously; browser actions return
outcome='queued' with payload.ticket_id and the caller polls
actionlayer_get_action_ticket until is_terminal=true. While
the ticket is pending there is no sub-status — keep polling.
| Name | Required | Description | Default |
|---|---|---|---|
| inputs | Yes | ||
| executor | No | ||
| action_id | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that API actions run synchronously, browser actions return outcome='queued' with a ticket_id to poll, and that while pending there is no sub-status. Also notes that additionalProperties in inputs are rejected.
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 main purpose, each sentence adds value with no redundancy. Concise yet informative.
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?
Output schema exists so return values need not be explained. Covers behavior and distinctions from siblings, but could mention the purpose of the executor parameter.
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 0% schema coverage, description compensates by explaining that inputs must match the action's input_schema exactly and that additionalProperties are rejected. However, it does not detail the executor or action_id parameters beyond what schema provides.
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?
Clearly states it invokes a single action with typed inputs, and distinguishes from sibling actionlayer_start_task by specifying that envelope metadata belongs in the latter.
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 tells when to use this tool versus actionlayer_start_task, and explains synchronous vs async behavior with polling instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_list_actionsAInspect
What ActionLayer can do, as prose. Read this when you're deciding whether ActionLayer fits the user's request, or when you're picking which entry point to call. The response is a single 'description' field — there is no catalog of typed actions to enumerate, by design.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description fully covers behavior: it returns a single 'description' field and notes there is no catalog of typed actions, which is transparent.
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?
Highly concise: two sentences that front-load purpose and usage, with 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 tool with a simple output (single field), the description is complete, covering purpose, usage, and return format.
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?
Zero parameters, so baseline is 4. The description adds no parameter info, but none 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 states the tool returns a prose description of ActionLayer's capabilities, distinguishing it from sibling tools that perform specific actions like canceling or creating jobs.
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 tells when to use: when deciding if ActionLayer fits the request or when picking an entry point, implying use before other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_list_skillsCInspect
List skills registered for this user.
| Name | Required | Description | Default |
|---|---|---|---|
| flow | No | ||
| limit | No | ||
| lifecycle | No | ||
| source_format | No |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits but only states basic functionality. It omits whether the tool has side effects, requires authentication, or includes performance implications, leaving the agent without critical 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?
While concise at one sentence, the description is underspecified, lacking essential details. Effective conciseness requires conveying necessary information without excess; here, it sacrifices substance for brevity.
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?
Given the four optional parameters and the existence of an output schema, the description fails to provide sufficient context about parameter effects or return format, leaving significant gaps 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 description coverage is 0%. The description adds no explanation for the four optional parameters (flow, limit, lifecycle, source_format), leaving the agent to infer their meaning from names alone.
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 action (list) and the resource (skills) with a specific scope (for this user). It effectively distinguishes from sibling tools, which focus on jobs, actions, and tasks.
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 provided on when to use this tool versus alternatives, nor any context about prerequisites or constraints. The description is purely functional without usage recommendations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_provide_credentialsAInspect
Submit credentials for an action ticket blocked with creds_required. Stored ephemerally in Redis (15-min TTL, single-use GETDEL), never written to Postgres or logs.
| Name | Required | Description | Default |
|---|---|---|---|
| fields | Yes | ||
| ticket_id | Yes | ||
| remember_for_session | No |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden; it details ephemeral Redis storage with 15-min TTL, single-use GETDEL, and confirms data is never written to Postgres or logs, fully disclosing behavioral traits.
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 concise sentences, front-loaded with purpose, no superfluous words, every sentence adds value.
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?
Output schema exists so return value not needed, storage details are thorough, but lack of parameter documentation leaves a gap; adequate but not 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?
Schema description coverage is 0%, but description does not explain individual parameters (ticket_id, fields, remember_for_session) beyond mentioning 'credentials', failing to add meaning for the agent.
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?
Description clearly states 'Submit credentials for an action ticket blocked with creds_required', using a specific verb and resource, and distinguishes from sibling tools by specifying the unique use case.
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 indicates when to use (ticket blocked with creds_required), providing clear context, but does not mention when not to use or offer alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_replyAInspect
Resume a ticket waiting on the user. If the next_action prompt is sensitive (2FA, password), pass sensitive=true and DO NOT echo the value to any other tool.
Info asks (ticket carries info_request): pass field_values
matching requested_fields ∪ question keys exactly.
Payment asks are approved in the user's Link app, never in
chat. When info_request.payment_status is
"pending_wallet_approval", tell the user to open Link on
their phone and approve there. payment_approved=false
declines the charge (task fails); payment_approved=true
re-sends the approval push after it expired
(payment_status="approval_expired").
| Name | Required | Description | Default |
|---|---|---|---|
| field | No | ||
| value | No | ||
| message | No | ||
| sensitive | No | ||
| ticket_id | Yes | ||
| field_values | No | ||
| payment_approved | No |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses behavior for sensitive prompts (no echo), info asks (exact field_values), and payment asks (approval via Link app, payment_approved semantics, task failure on false). Does not cover rate limits or auth, but core behavioral traits are transparent.
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?
Description is structured with paragraphs for different scenarios, front-loading the main action. It is informative but slightly verbose; each sentence adds value, but could be more concise by combining related instructions. Overall well-organized.
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?
Given 7 parameters and existing output schema, the description covers critical scenarios (sensitive, info, payment) thoroughly. It explains complex payment flow and sensitive data handling. However, it omits details on general reply parameters (field, value, message) and return format, leaving some gaps. Still, comprehensive for the tool's core use.
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%, so description must compensate. It explains sensitive, field_values, and payment_approved parameters in context. However, parameters 'field', 'value', and 'message' are not described; their purpose (likely for general replies) is unclear. Description adds significant value for three key parameters but leaves others ambiguous.
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 tool resumes a ticket waiting on the user. It distinguishes from sibling tools (e.g., cancel, create_job) by specifying the action and conditions. The verb 'Resume' and context of sensitive/info/payment asks make the purpose 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?
Explicitly describes when to use the tool: to resume a ticket. Provides conditional guidance for sensitive prompts (pass sensitive=true, don't echo value), info asks (pass field_values matching requested fields), and payment asks (tell user to approve in Link app). Implicitly excludes usage for non-resume actions, offering clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_resume_jobAInspect
Resume a job that's in 'blocked' state. Use after the user has resolved the blocker (e.g. replied to a prompt or provided credentials).
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It implies state transition from blocked to active and clarifies precondition (blocked state). However, it does not detail effects like whether job runs synchronously or what happens on failure.
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, direct and front-loaded with the action and condition. 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?
Description is minimal but covers core action and trigger. Output schema exists but description does not hint at response or next steps. For a simple tool with one param, it is sufficient though not exhaustive.
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 has 0% description coverage; only parameter is 'job_id' with no type details beyond string. Description does not explain job_id's role or format, leaving the agent with no guidance beyond the name.
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?
Description clearly states the verb 'Resume', the resource 'job', and the specific condition 'blocked state'. It uniquely distinguishes from siblings like 'actionlayer_cancel_job' or 'actionlayer_get_job' by focusing on resumption after blocker resolution.
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 states when to use: after user has resolved the blocker. Provides clear context but does not mention when not to use or suggest alternatives, though siblings imply different scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_start_taskAInspect
Execute a real-world goal on the web — book, order, fill, click, log in, extract, automate. Use this when the user wants something DONE on a live website (Resy, Amazon, any URL), not when they want analysis or text.
An AI agent runs the task end-to-end on the live web — it reads the page and adapts to whatever it finds (CAPTCHA, novel UI, login wall, weird checkout). Tickets that would normally fail on a hard step just keep progressing. You don't need to design around the unhappy path.
Prefer actionlayer_invoke_action with a typed action id when one fits — it's faster and more deterministic. Reach for actionlayer_start_task when no typed action covers the site, or when the goal mixes multiple steps.
Be SPECIFIC. The goal must include: which site/place, when, how many, exact product URL if buying. Vague goals ("book me dinner", "order something") block on the user and waste planning budget — ask the user for the missing pieces FIRST, then call this with everything nailed down.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | Specific natural-language description. Good: "Book a table for 2 at Bar Crenn (SF) on 2026-12-06, 7-8:30pm via Resy" Bad: "find me a flight" (too vague — will block) | |
| webhook_url | No | Optional. Best-effort POST (single attempt, no retries) when the ticket blocks on user input or reaches a terminal state. Thin payload {kind, ticket_id, state, occurred_at} — treat it as a poke and call actionlayer_get_task for the details. Polling works with or without it. | |
| max_budget_usd | No | Required for anything that spends money. The planner soft-caps spend and escalates instead of overspending. | |
| idempotency_key | No | Optional caller-supplied retry key — same key within 24h returns the same ticket. |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that an AI agent runs the task end-to-end, adapts to CAPTCHA/login walls, and that tickets progress on hard steps. Mentions webhook behavior and budget soft-cap. However, it could be more explicit about idempotency handling and potential side effects.
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 well-structured and front-loaded. First paragraph states purpose, second gives behavioral context and preference for alternative, third provides critical usage advice. Every sentence adds value with 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?
Given the complexity, parameter count, and presence of output schema, the description covers all essential aspects: purpose, usage, behavioral traits, parameter advice, and differentiation from siblings. It does not need to detail return values as output schema exists.
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 parameters are fully described. The description adds valuable guidance on goal specificity and examples, reinforcing the schema. The webhook parameter behavior is well explained in the description.
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 that the tool executes real-world goals on the web (book, order, fill, click, log in, extract, automate). It also distinguishes itself from the sibling tool actionlayer_invoke_action by specifying when to prefer that alternative.
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 explicit when-to-use (user wants something done on a live website) and when-not-to-use (analysis or text). Explicitly names the alternative actionlayer_invoke_action with conditions for preference. Also advises on being specific and asking for missing details.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
actionlayer_submit_feedbackAInspect
Leave feedback on a finished task. rating is "good" or
"bad"; comment is an optional free-text note. Only valid once
the ticket is completed or failed. One per task — calling again
overwrites the previous rating/note.
| Name | Required | Description | Default |
|---|---|---|---|
| rating | Yes | ||
| comment | No | ||
| ticket_id | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description fully discloses the tool's mutability (overwrites), precondition (completed/failed ticket), and the fact that it is for finished tasks. This is sufficient for a feedback tool.
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 adding distinct value. Front-loaded with the main action. No unnecessary 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?
Covers purpose, parameters, timing constraint, and overwrite behavior. An output schema exists (not shown) so return values are not needed. This is fully adequate for a simple feedback 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?
Schema description coverage is 0%, but the description adds essential meaning: rating is 'good' or 'bad', comment is optional free-text, and ticket_id is the required target. This compensates fully.
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 a clear verb ('Leave feedback') and resource ('on a finished task'), and distinguishes itself from sibling tools that handle canceling, creating jobs, etc.
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 states when the tool is valid ('Only valid once the ticket is completed or failed') and its idempotency behavior ('One per task — calling again overwrites'). While it doesn't explicitly name alternatives, the sibling list provides context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!