Skip to main content
Glama
Sign In
AIWorkhub

AIWorkhub

by shrec
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

needfix_preview_convert

Preview a workforce-bound task conversion and see the plan digest, validation role requirements and a condensed plan summary before committing, without resending the full plan.

Instructions

Preview an explicit workforce-bound task conversion.

The reply keeps plan_digest, plan_digest_accepted_alone and validation_roles_requirement -- the three facts the commit decision actually turns on -- and folds the signed plan body to its identity plus title/runner/topic/work_kind and the allowed_writes and required_outputs counts. include_plan=true returns the plan verbatim. Measured 2026-10-09 on NF-2026-01452: ~6 KB of plan echoed three times, because convert then refused plan_digest alone (NF-2026-01447). It no longer does, so the previewed plan never has to be resent.

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": {
      "needfix_id": "<needfix_id>"
    },
    "name": "needfix_preview_convert"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_planNoTask card fields that override the scope-derived default; a writable card needs required_outputs. Omitted runner/topic are filled from aiworkhub_manager_workforce_rank top-1 (reply filled_from), an acceptance string becomes a one-item list, and stray action/task_id keys are dropped with a warning; every change is listed under plan_normalizations and plan_digest binds the normalized plan. Other unknown fields are refused. An optional evidence string (up to 16000 characters) is carried onto the created card; it is not part of plan_digest and a digest-only convert reuses the evidence this preview held.
needfix_idYesNeedFix id, e.g. NF-2026-01447.
include_planNoReturn the signed plan body verbatim instead of a summary of its identity and counts; default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.12.98
    • changedInput schema / properties / task_plan / description
      Previous value: -"Task card fields that override the scope-derived default; a writable card needs required_outputs. Omitted runner/topic are filled from aiworkhub_manager_workforce_rank top-1 (reply filled_from), an acceptance string becomes a one-item list, and stray action/task_id keys are dropped with a warning; every change is listed under plan_normalizations and plan_digest binds the normalized plan. Other unknown fields are refused."New value: +"Task card fields that override the scope-derived default; a writable card needs required_outputs. Omitted runner/topic are filled from aiworkhub_manager_workforce_rank top-1 (reply filled_from), an acceptance string becomes a one-item list, and stray action/task_id keys are dropped with a warning; every change is listed under plan_normalizations and plan_digest binds the normalized plan. Other unknown fields are refused. An optional evidence string (up to 16000 characters) is carried onto the created card; it is not part of plan_digest and a digest-only convert reuses the evidence this preview held."
  2. Changed1 schema field changedv0.12.87
    • changedInput schema / properties / task_plan / description
      Previous value: -"Task card fields that override the scope-derived default; must name runner and topic, and a writable card needs required_outputs. Unknown fields are refused."New value: +"Task card fields that override the scope-derived default; a writable card needs required_outputs. Omitted runner/topic are filled from aiworkhub_manager_workforce_rank top-1 (reply filled_from), an acceptance string becomes a one-item list, and stray action/task_id keys are dropped with a warning; every change is listed under plan_normalizations and plan_digest binds the normalized plan. Other unknown fields are refused."
  3. Changed3 schema fields changedv0.12.67
    • addedInput schema / properties / include_plan / description
      Added value: +"Return the signed plan body verbatim instead of a summary of its identity and counts; default false."
    • addedInput schema / properties / needfix_id / description
      Added value: +"NeedFix id, e.g. NF-2026-01447."
    • addedInput schema / properties / task_plan / description
      Added value: +"Task card fields that override the scope-derived default; must name runner and topic, and a writable card needs required_outputs. Unknown fields are refused."
  4. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false, destructiveHint=false, openWorldHint=false, which is counterintuitive for something called a 'preview' and unexplained. The description compensates by disclosing that the preview holds evidence that a digest-only convert reuses, that the reply is folded to identity and counts, and roughly how large the payload is — real behavioral context beyond the annotations. It still doesn't say what side effect makes this non-read-only.

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 first sentence is well front-loaded, but the trailing measurement — a date, ticket IDs NF-2026-01452 and NF-2026-01447, and '~6 KB of plan echoed three times' — reads as changelog rationale rather than selection guidance an agent can act on. The payload-shape sentence is dense but does earn its place; the historical justification does not.

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?

There is no output schema, so the description must describe the return value, and it does: it names plan_digest, plan_digest_accepted_alone, validation_roles_requirement, and the folded plan fields and counts, plus the include_plan override. What is missing is why those three fields matter for the commit call and what error or rejection looks like, but for a three-parameter tool this is close to sufficient.

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 coverage is 100%, so the schema already documents task_plan, needfix_id, and include_plan thoroughly, including normalization rules and the evidence field. The description restates include_plan's behavior ('returns the plan verbatim') without adding syntax or constraints, and its note about evidence reuse is the only marginal addition. Baseline 3 is appropriate.

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 opening sentence names a specific verb and resource: preview an explicit workforce-bound task conversion. The later reference to 'convert then refused plan_digest alone' and 'the previewed plan never has to be resent' implicitly positions it ahead of needfix_convert, but no sibling is named outright, so an agent must infer the pairing rather than read it.

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

Usage Guidelines3/5

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

Usage is only implied: preview, then commit with the digest. The description hints at the workflow via 'the commit decision' and 'digest-only convert,' but never states when to call this instead of needfix_convert directly, nor any prerequisite such as whether a needfix must be in a particular state.

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

Deploy Server

Other Tools