Skip to main content
Glama

TrueInterview

Keep a note for me

save_context_note
Idempotent

Keep one short note for the candidate on TrueInterview, so the agents they connect know it next time: a goal, the companies they target, a constraint (a start date, a place they cannot move from) or a preference. Save only what the candidate asked you to keep, or agreed to when you offered, in their words, and tell them what you saved. Never the conversation itself, a guess, a self-identification answer (gender, ethnicity, veteran status, disability) or anything about someone else. A bank card or government ID number, a password or a token is refused and nothing is saved, and so is a note with fewer than three letters or digits. Saving the same note again changes nothing; with no topic, the same words under any topic count as the same note, and a new one is filed under "other". They can ask you to show or delete any note.

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": {
      "text": "<text>"
    },
    "name": "save_context_note"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe note in the candidate's words, at most 1,000 characters.
topicNoLeft out: filed under "other".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare the write, non-destructive, idempotent profile, and the description usefully extends that with dedupe mechanics (same words re-saved change nothing; topic-insensitive matching when no topic is given) plus refusal conditions for secrets and very short notes. It does not say how a refusal is surfaced to the caller (error vs. silent no-op), which is the one behavioral detail left open beyond the annotations.

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 and nearly every clause carries a rule (consent, exclusions, refusals, dedupe, default topic). It is a dense single paragraph with minor repetition ("in their words" appears twice, "note" recurs), so it is efficient rather than tight.

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 a two-parameter mutation tool with annotations and no output schema, this covers consent, prohibited content, refusal cases, idempotency, and defaulting thoroughly. The remaining gap is what the caller observes on a refused or duplicate save, which matters for an agent deciding whether to report success.

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%, so the baseline is 3, but the description adds real semantics the schema lacks: how an omitted topic interacts with duplicate detection and that the default bucket is "other". The 1,000-character cap is only in the schema, but that is acceptable given full coverage.

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?

States a specific verb and resource ("Keep one short note for the candidate on TrueInterview") and immediately enumerates the kinds of content it holds (goal, target companies, constraint, preference), which separates it from sibling note tools like list_context_note and delete_context_note. An agent can tell what this writes and what it does not 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 Guidelines5/5

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

Gives an explicit trigger (only what the candidate asked to keep or agreed to when offered, in their words) and explicit exclusions (never the conversation itself, a guess, self-identification data, information about someone else). It also routes the show/delete cases to other operations, so the boundary of this tool is unambiguous.

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