Skip to main content
Glama

Check an application run

getApplicationRun
Read-onlyIdempotent

See how an applyToJob run went. state is running, finished or crashed. When finished, outcome is submitted (sent and confirmed by the employer's site; it is on their tracker as applied), submit_unconfirmed (submit clicked but no confirmation; do not resend), ready_to_submit (a dry run, every field filled, nothing sent), needs_input (nothing sent; ask the candidate each question in needsInput, then call applyToJob again with answers), blocked (a CAPTCHA or login wall, see blockers) or failed (nothing was sent, see blockers for why). A profile_gap question is worth saving to the candidate's profile with editPreferences too. editable lists the answers Clera filled in for them (question, answer, options); when the candidate wants one changed, call applyToJob again with answers { : }. verificationCodeRequested means the employer emailed a code: if the run applied with the Clera apply address it usually reaches the form on its own, so check again and look in readApplyInbox before asking the candidate for it.

Clera privately records this tool's inputs and results for usage tracking and support.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "runId": "<runId>"
    },
    "name": "getApplicationRun"
  }
}

Input Schema

NameRequiredDescriptionDefault
runIdYesThe runId applyToJob returned.

Output Schema

NameRequiredDescriptionDefault
errorYes
stateYes
fieldsYes
outcomeYes
blockersYes
editableYes
needsInputYes
resumeAttachedYes
verificationCodeRequestedYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered without the description. The description does add genuinely new behavioral context the annotations cannot convey – that nothing was sent in the ready_to_submit, needs_input, blocked and failed outcomes, and that a submit_unconfirmed run must not be resent. However, it never explains polling cadence for a run still in 'running' state, which is the main behavioral question for a status-check tool, so it stops short of full transparency.

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

Conciseness2/5

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

The content is dense and front-loaded, but it is delivered as two long run-on sentences with nested parentheses covering state values, six outcome values, the editable-answers flow and the verification-code flow. A short structured list of outcomes with their required next action would be far easier to parse. The closing privacy/usage-tracking sentence is boilerplate that does not help the agent decide or invoke.

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

Completeness5/5

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

An output schema exists, so return-value explanation is not required, yet the description still explains the meaning of every outcome value and the blockers/needsInput/editable fields an agent will encounter. For a one-parameter read tool, this covers everything an agent needs to interpret a result and choose the correct follow-up call.

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

Parameters3/5

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

There is only one parameter and schema coverage is 100%, with the schema itself stating 'The runId applyToJob returned.' The description reinforces that provenance by framing the tool as a lookup of an applyToJob run, but adds no syntax, format, length, or error semantics beyond what the schema already documents, so the baseline of 3 applies.

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

Purpose5/5

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

The opening sentence gives a specific verb and resource ('See how an applyToJob run went') and immediately ties the tool to its sibling applyToJob, so the agent knows this is a status-check on a specific run rather than a search or a mutation. The enumeration of state values (running, finished, crashed) further pins down what is being reported.

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

Usage Guidelines5/5

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

The description is unusually prescriptive about next actions: on needs_input it says to ask the candidate each question in needsInput and then call applyToJob again with answers; on submit_unconfirmed it explicitly says 'do not resend'; on an editable answer it specifies the exact follow-up call and payload shape; on verificationCodeRequested it says to check again and look in readApplyInbox before asking the candidate for the code. These are concrete when/when-not/alternative instructions rather than implied usage.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources