Skip to main content
Glama

Edit rejection reasons

editRejectionReasons
Destructive

Record or remove why the company rejected candidates for a role. These reasons shape future matching. add: jobId + rawReason + paraphrasedReason + clientQuote, optional talentId and categories: record why a candidate was rejected. Even brief feedback improves future matching; the paraphrased version should generalize away from the specific candidate, and clientQuote is the client's message copied word for word. Set categories to every reason the feedback names: 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). Feedback that is exactly one of those names counts as it; anything else is kept as text only. delete: jobId + reasonId (from list): remove one reason. Get jobId from readJob list and reasonId from readRejectionReasons list.

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": {
      "command": "<command>"
    },
    "name": "editRejectionReasons"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdNolist/add/delete (required): the job UUID. Use the job tool's list command to find IDs.
orgIdNoOrganization to act as. Only needed when you belong to more than one organization.
commandYesWhich operation to run: add | delete. The tool description explains each.
reasonIdNodelete (required): the reason id from a list call.
talentIdNoadd (optional): the rejected talent's UUID, to track patterns per candidate.
rawReasonNoadd (required): the company's verbatim rejection feedback.
categoriesNoadd (optional): every reason from the list in the tool description that this feedback names.
clientQuoteNoadd (required): the client's own words, copied verbatim from their message, never rephrased, summarised or corrected. For a bare 'no' pass the bare 'no'. This is what Clera stores as the client's feedback; rawReason and paraphrasedReason stay on the role.
paraphrasedReasonNoadd (required): a generalized version for future matching, not specific to one candidate.

Output Schema

NameRequiredDescriptionDefault
messageYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already flag mutation and destructiveness (readOnlyHint=false, destructiveHint=true), so the description is not the only source of the safety profile. It adds real behavior context beyond that: the paraphrase-generalizes-away-from-the-candidate rule, the verbatim clientQuote rule, the note that rawReason/paraphrasedReason stay on the role while clientQuote is what Clera stores, and a data-tracking disclosure. It stops short of saying removal is irreversible or naming permission requirements.

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?

Purpose is front-loaded, then structured under 'add:' and 'delete:' headings, which makes the dense content scannable. The long inline taxonomy is justified because it carries enum semantics, though some repetition ('Even brief feedback improves future matching') could be trimmed.

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 mutation tool with nine parameters, two commands, and an output schema present, the description covers operation selection, per-field intent, ID sourcing, the enum taxonomy, and the storage/tracking caveat. Nothing material is left for the agent to infer before a correct call.

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 100%, so the baseline would be 3, but the description genuinely adds meaning the schema cannot: it defines all nine category values in plain language (too_senior, below_talent_bar, visa, etc.) where the schema only lists the enum strings, and it clarifies the boundary case ('Feedback that is exactly one of those names counts as it; anything else is kept as text only'). It also explains the intended content of paraphrasedReason and clientQuote, which the schema only states tersely.

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?

Opening sentence gives a specific verb pair and resource ('Record or remove why the company rejected candidates for a role') and adds the consequence ('These reasons shape future matching'). It is immediately distinguishable from the readRejectionReasons sibling, which is named later as the source of reasonId.

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

Usage Guidelines4/5

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

It splits usage by command ('add:' vs 'delete:') and states exactly which fields each requires, plus where to obtain the identifiers ('Get jobId from readJob list and reasonId from readRejectionReasons list'). It does not explicitly say to use readRejectionReasons instead when the goal is merely to view reasons, so the exclusion is implied rather than stated.

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