Skip to main content
Glama

Pass on a candidate

passCandidate
Destructive

Pass on a candidate for one role. Every reason you name trains the next list Clera sends for this role, so pick each one the user's words name and put their words in reason; your own view of the candidate goes in assistantNote. Reasons: too_senior (more senior than the role needs), too_junior (not senior enough yet), missing_skills (a must-have skill or stack is missing), wrong_background (career path or domain doesn't match), below_talent_bar (not strong enough for this team), location_mismatch (location or remote setup doesn't work), salary_expectations (the comp ask is above the range), visa (needs sponsorship or a work permit the company can't give), already_in_pipeline (the company already knows them), other (anything else; say what in reason). Both are optional, but a pass with neither tells Clera nothing about what to change. Passing again with a new reason replaces the old one. Only pass when the user asked to.

Works for a candidate from a search result, from listPendingIntroRequests or listRecommendedCandidates, or someone already in the pipeline (introduced, interviewing or at offer) from listPipeline. Target either a candidate from searchCandidates or similarCandidates (talentId, with jobId or the interactive role picker), or a list entry (its opportunityId, with talentName and roleName copied verbatim from that entry; all three must describe one entry). If the candidate and role you were asked about are not on the page you fetched, re-call the same list with roleId to narrow, or with offset or a larger candidatesPerStage to page further; if the pair does not exist, say so and pass on nothing. Passing a different role for the same candidate is refused. This marks the opportunity as no_fit (creating the opportunity record first when the candidate came straight from search) and logs the company's decision with their feedback.

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

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "passCandidate"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdNoWith talentId: the open role the pass is about. Resolve the id yourself with the job tool's list command when the user already named a role; when the role is not settled, omit it and the user gets an interactive role picker.
orgIdNoOrganization to act as. Only needed when you belong to more than one organization.
reasonNoWhat the user said about why this candidate is not a fit, in their own words, quoted or lightly trimmed and in their voice, e.g. 'We need someone who has written Rust.' No lead-in such as 'the hiring manager said' or 'per the user'. Never fill it from the profile, fit flags or job notes; that belongs in assistantNote. When the user gave no reason, ask once if the conversation allows it, otherwise leave it out. A sentence that fits any candidate is not a reason. Stored with the pass and shown to Clera.
roleNameNoWhen acting on a listed opportunity, the role name copied verbatim from the same row. Checked against the record; a mismatch is refused, so never substitute a different role for the same talent.
talentIdNoAlternative target: the candidate's id exactly as returned by searchCandidates or similarCandidates. Pair it with jobId.
categoriesNoEvery reason from the list in the tool description that the user's own words name. Leave it out when they named none.
talentNameNoWhen acting on a listed opportunity, the talent's name copied verbatim from that row. Checked against the record; a mismatch is refused. Omit on the talentId path.
assistantNoteNoYour own remarks for Clera, kept apart from the user's reason and never shown as the company's view: what the profile or fit flags say, a profile fact that contradicts what the user said, something to check. Leave it out when you have nothing to add.
opportunityIdNoThe opportunity ID from listPendingIntroRequests, listRecommendedCandidates or listPipeline.

Output Schema

NameRequiredDescriptionDefault
messageYes
outcomeYes
roleNameYes
talentNameYes
opportunityYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only say destructive=true and idempotent=false; the description adds real behavioral context beyond that: creating an opportunity record when the candidate came from search, overwriting a prior reason on re-pass, refusing cross-role passes, and logging the company's feedback. It also discloses that inputs/results are retained for usage tracking, which an agent should know before invoking a destructive tool.

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

Conciseness4/5

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

The opening paragraph front-loads purpose, the reason taxonomy, and the reason/assistantNote split, and every later paragraph covers a distinct concern (targeting, recovery, side effects). It is dense to the point of being a wall of text for a nine-parameter tool, and the closing privacy sentence is boilerplate, but nothing is redundant with structured fields.

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?

For a destructive, nine-parameter mutation with an output schema and full schema coverage, the description still covers the gaps an agent would otherwise hit: identifier pairing rules, paging recovery, refusal behavior, record creation, and reason overwriting. Nothing needed to call it correctly or to avoid a wrong-target pass is missing.

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

Parameters5/5

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

Schema coverage is already 100%, yet the description still adds meaning the schema does not: it enumerates and defines all ten reason categories (the schema's categories field just points back to the description), and it draws a sharp boundary between the user's quoted words in `reason` versus the agent's own observations in `assistantNote`. It also explains when to omit jobId in favor of the interactive role picker.

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 first sentence names a specific verb and resource with scope ('Pass on a candidate for one role'), and later text states the concrete effect: the opportunity becomes no_fit and the decision is logged with feedback. The three accepted target paths (search result, list entry, existing pipeline record) let an agent tell it apart from sibling list/read tools without opening schemas.

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?

Explicit gating is given ('Only pass when the user asked to'), plus when to supply which identifier pair, how to recover when the candidate/role pair is not on the fetched page (re-call with roleId, offset, or larger candidatesPerStage), and when to pass on nothing at all. Refusal conditions ('a different role for the same candidate is refused', verbatim name/role mismatch) are stated as exclusions, not left to inference.

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