Skip to main content
Glama

Like a match

likeMatch
Idempotent

Tell Clera the candidate wants this role, the same as the like button on a Matches card. Works on a match and on an open_role row alike.

A like can put the candidate in front of the company: Clera checks the fit against the role, may ask the candidate to answer the role's questions first (listMatches shows them as status questions), and submits them to the company when it fits, which cannot be taken back. Confirm the role with the candidate before liking, and say it went to Clera for review rather than "applied".

A row with applyOwnership referral_link (a role Clera found through a partner such as micro1) works differently: there is no intro and nothing is submitted for the candidate. The like returns referralUrl, the partner's own application page; the candidate creates an account there and finishes the application themselves. Hand them that link, say the role finishes on the partner's side, and never promise an intro for it.

Pass position and companyName exactly as the row gave them; a mismatch is refused rather than liking the wrong role. Liking twice changes nothing. The dashboard can take up to a minute to show the change.

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": {
      "jobId": "<jobId>",
      "position": "<position>",
      "companyName": "<companyName>"
    },
    "name": "likeMatch"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdYesThe jobId from a listMatches or listMyPipeline row.
positionYesThe position exactly as the row gave it.
companyNameYesThe company name exactly as the row gave it.

Output Schema

NameRequiredDescriptionDefault
jobIdYes
statusYes
positionYes
companyNameYes
referralUrlYes
opportunityIdYes
applyOwnershipYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=true), the description discloses that a successful like can submit the candidate to the company and that this cannot be taken back, which is the single most consequential fact about the tool. It also covers the divergent referral-link path (returns referralUrl, nothing is submitted), validation refusal on position/companyName mismatch, and up to a minute of dashboard lag. The irreversibility language sits in mild tension with destructiveHint=false, but it describes an irreversible outbound submission rather than data destruction, so it is not a contradiction.

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?

Front-loaded with purpose in the first sentence, then a paragraph each for the standard path and the referral path, so an agent can stop reading once it knows which path applies. It is on the long side and the Matches-card analogy plus the repeated 'exactly as the row gave it' phrasing cost a little, but nearly every sentence carries operational weight.

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?

The tool is a consequential mutation with an output schema, and the description covers the decision-relevant surface: who sees the result, how the referral variant returns a different artifact, what is refused, and what the agent should tell the candidate. Nothing needed to call it correctly or to narrate the outcome is missing.

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

Parameters4/5

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

Schema coverage is 100% and the schema already states that position and companyName must match the row, so the baseline is 3. The description still earns a point by adding the consequence the schema omits: a mismatch is refused rather than liking the wrong role, and jobId is traced to listMatches or listMyPipeline rows. That turns three opaque strings into a matched-triple contract.

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 names a specific action (telling Clera the candidate wants this role) and anchors it to a familiar mental model, the like button on a Matches card. It also distinguishes this action from applying ("say it went to Clera for review rather than 'applied'") and names listMatches as the source of the rows and status questions, so an agent can tell it apart from declineMatch or applyToJob.

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 preconditions are given: confirm the role with the candidate before liking, and never promise an intro when the row carries applyOwnership referral_link. It also states the post-call behaviors that matter — the candidate may be asked to answer the role's questions first, and liking twice changes nothing — so the agent knows when this tool is the right call and what to expect afterward.

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