Skip to main content
Glama

ceevee_confirm_lens

Positioning step 3 of 3 (5 credits, 20-30 s): targeted CV edits for the lens the user chose, before/after with trade-offs, and PDF links. For richer edits pass what steps 1 and 2 returned (positioning_snapshot, detected_lens_full, recruiter_inference, selected_opportunities).

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": {
      "cv_version_id": "<cv_version_id>",
      "confirmed_lens": "<confirmed_lens>"
    },
    "name": "ceevee_confirm_lens"
  }
}

Input Schema

NameRequiredDescriptionDefault
session_idNoFrom ceevee_analyze_positioning
cv_version_idYesFrom ceevee_list_versions
confirmed_lensYesThe lens the user chose
custom_positioningNo
detected_lens_fullNo
recruiter_inferenceNo
positioning_snapshotNo
selected_opportunitiesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • changedInput schema / properties / confirmed_lens / description
      Previous value: -"The lens confirmed by user (from ceevee_analyze_positioning output)"New value: +"The lens the user chose"
    • removedInput schema / properties / custom_positioning / description
      Removed value: -"Optional custom positioning description"
    • changedInput schema / properties / cv_version_id / description
      Previous value: -"CV version ID from ceevee_upload_cv or ceevee_list_versions"New value: +"From ceevee_list_versions"
    • removedInput schema / properties / detected_lens_full / description
      Removed value: -"Full detected lens data from ceevee_analyze_positioning"
    • removedInput schema / properties / positioning_snapshot / description
      Removed value: -"Market positioning snapshot from ceevee_analyze_positioning"
    • removedInput schema / properties / recruiter_inference / description
      Removed value: -"Recruiter inference data from ceevee_analyze_positioning"
    • removedInput schema / properties / selected_opportunities / description
      Removed value: -"Selected opportunities from ceevee_get_opportunities"
    • changedInput schema / properties / session_id / description
      Previous value: -"Session ID from ceevee_analyze_positioning (step 1)"New value: +"From ceevee_analyze_positioning"
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

The annotations only declare a non-read-only, non-idempotent, open-world, non-destructive operation; the description adds genuinely useful operational facts not in those fields — a 5-credit cost and 20-30 s latency per call, which matter a lot given idempotentHint=false implies repeat calls are billed again. The main gap is that it never says whether the edit mutates cv_version_id in place or produces a new version, which is the key behavioral question for a non-idempotent write tool.

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

Conciseness5/5

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

Two sentences, both dense with decision-relevant information: step position, cost, latency, and output contents come first, with the optional parameter guidance second. There is no filler and nothing redundant with the schema.

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

Completeness4/5

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

For an 8-parameter, nested-object, no-output-schema mutation tool, the description covers what an agent most needs — cost, duration, what comes back, and how to enrich the call via prior steps. It is only slightly incomplete on persistence semantics (in-place edit vs new version) and on what custom_positioning does.

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 only 38%, and the four pass-through parameters (positioning_snapshot, detected_lens_full, recruiter_inference, selected_opportunities) carry no descriptions at all — the description compensates by explaining they are outputs of steps 1 and 2 and that supplying them yields richer edits, which is real added meaning. Only custom_positioning remains unexplained in both schema and description.

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 description names a specific verb and resource — 'targeted CV edits for the lens the user chose' — and situates it as 'positioning step 3 of 3', which tells an agent exactly where it sits in the ceevee chain relative to analyze_positioning and the get/list siblings. It also states the output shape (before/after with trade-offs, PDF links), so the tool is distinguishable without opening the schema.

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?

'Positioning step 3 of 3' plus 'before/after' clearly frames this as the confirmation stage that follows analysis, and the second sentence directs the agent to pass earlier step outputs for richer results. It stops short of stating explicit exclusions or naming an alternative tool for a plain no-edit retrieval, so it is clear context rather than a full when/when-not rule set.

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