Skip to main content
Glama

Guided Interview

faf_go
Destructive

Returns the Table-of-8 project context slots with scores, identifies which need answers, and writes confirmed answers into project.faf to update the score.

Instructions

The human half of project.faf. Without answers it returns the Table-of-8 — project name, goal and the 6Ws (who, what, why, where, when, how) — each filled, seeded from the goal, or empty, with faf-cli's score and, for each slot still empty, whether it is a fact from repo (faf_auto writes it: its dry run, the one faf_formats shows) or needs an answer here. An empty goal or W carries faf-cli's suggestion from the repo with its source, for the user to confirm. With answers (slot path → the text the user confirmed, e.g. {"human_context.why": ""}) it writes them into /project.faf in place and returns the new score; a value already in a slot you answer is replaced. With no project.faf yet it runs faf_init and faf_auto first. faf_auto writes each fact from repo; a stack slot with no fact in repo is answered here.

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": "faf_go"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoProject path. Sets session context for subsequent calls.
answersNoAnswers to apply: a slot path (e.g. "project.goal", "human_context.why", "stack.database") → the text the user confirmed. Any other key, or an answer that is not text, is refused and nothing is written. If provided, applies the answers and returns the new score.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv7.2.1
    • changedInput schema / properties / answers / description
      Previous value: -"Answers to apply: a slot path (e.g. \"project.goal\", \"human_context.why\", \"stack.database\") → the answer text. Any other key, or an answer that is not text, is refused and nothing is written. If provided, applies the answers and returns the new score."New value: +"Answers to apply: a slot path (e.g. \"project.goal\", \"human_context.why\", \"stack.database\") → the text the user confirmed. Any other key, or an answer that is not text, is refused and nothing is written. If provided, applies the answers and returns the new score."
  2. Changed1 schema field changedv6.0.0
    • changedInput schema / properties / answers / description
      Previous value: -"Answers to apply. Keys are field paths (e.g., \"project.goal\", \"human_context.why\"), values are the answers. If provided, applies answers and returns new score."New value: +"Answers to apply: a slot path (e.g. \"project.goal\", \"human_context.why\", \"stack.database\") → the answer text. Any other key, or an answer that is not text, is refused and nothing is written. If provided, applies the answers and returns the new score."
  3. First observedv4.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and non-idempotent, and the description adds the concrete cause: 'a value already in a slot you answer is replaced' and an existing slot's content is overwritten in place. It also discloses the hidden side effect of auto-running faf_init and faf_auto when no project.faf exists. It does not discuss what happens on partial failure or the shape of the returned score beyond 'the new score'.

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

Conciseness3/5

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

The content is information-dense with little filler, but it is delivered as a run-on block mixing purpose, mode behavior, sibling routing and error handling, and it leads with the vague 'The human half of project.faf.' Several terms are undefined, hurting front-loading and parseability.

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, no-output-schema tool with nested answers, the description covers both modes, the returned table contents including score and source, the auto-init side effect, and overwrite behavior. Remaining gaps are the undefined 'Table-of-8' and 'fact from repo' vocabulary rather than missing operational facts.

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

Parameters3/5

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

Schema description coverage is 100%, so both parameters are already documented, including the slot-path → text mapping and the refusal of non-text or unknown keys. The description adds only marginal meaning, chiefly the replacement semantics for answers and the example slot path. Baseline 3 is appropriate since the schema carries the load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete purpose: it surfaces the Table-of-8 (project name, goal, 6Ws) each filled/seeded/empty, and with answers it writes them into <folder>/project.faf and returns a score. It explicitly contrasts its role with siblings: 'The human half of project.faf', 'faf_auto writes each fact from repo; a stack slot with no fact in repo is answered here.' Clarity is reduced by unexplained jargon ('Table-of-8', 'faf-cli', 'fact from repo'), so it falls short of 5.

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 clearly delineates the two modes — call without answers to get the interview table, call with answers to apply them — and states the precondition behavior: 'With no project.faf yet it runs faf_init and faf_auto first.' It also routes the repo-fact cases to faf_auto. What is missing is any explicit statement of when an agent should prefer this over faf_score or faf_context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.