Skip to main content
Glama

fow_packet_author

Destructive

Author bounded implementation packets in Flower MCP with complete instructions, stable plan units, dependencies, contracts, and checks; resolve engineering questions before execution.

Instructions

Define the bounded implementation work in a packet: complete instructions, stable plan units, dependencies, producer/consumer contracts and checks. Resolve engineering questions through ordinary authoring before execution. Route with operation: start_packet, revise_packet, replace_plan, resolve_questions, answer_gate, add_unit, revise_unit, remove_unit, rebind_unit, set_dependencies. Prerequisites: Use current specification/plan revisions and ordinary packet authority; investigate and close semantic gaps before dispatch. Effects: Creates/revises packets and complete ordered units/contracts/dependencies. Removal/replacement changes current plan authority; provider-target deltas may be queued, without executing coding work. Exact help (replace operation_name with the selected route): fow_capabilities({"view":"operation","operation_tool":"fow_packet_author","operation_name":"start_packet"}).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
unitNoComplete bounded implementation-unit declaration, including instructions, targets, producer/consumer contracts and verification obligations as required by plan authority. Applies to: add_unit. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>).
actorYesIdentity of the human or agent recording this action; retain the original identity when replaying its request.
titleNoShort human-readable title of the authored requirement, finding, packet, run step or campaign. Applies to: start_packet, revise_packet. Required by: start_packet.
intentNoEngineering statement of the packet's intended observable behavior and authorized scope. Applies to: start_packet, revise_packet. Required by: start_packet.
answersNoStructured resolutions of the packet's currently open engineering questions, using their issued identities. Applies to: replace_plan, resolve_questions. Required by: resolve_questions. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>).
purposeNoCanonical packet purpose, including ordinary implementation or governed semantic remediation. Applies to: start_packet. Required by: start_packet. Canonical values: implementation, remediation.implementation
goal_idsNoExisting goal graph IDs governing the packet or campaign scope. Applies to: start_packet, revise_packet.
in_scopeNoBehaviors and implementation boundaries explicitly included in this packet. Applies to: start_packet, revise_packet.
responseNoStructured answer to the issued packet gate; use its current fingerprint and exact response contract. Applies to: answer_gate. Required by: answer_gate. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>).
change_idNoCanonical owning change ID; when address resolution permits omission, the packet/campaign must resolve unambiguously.
operationNoOperation selector for this multiplexer; use a canonical route listed below. Canonical values: start_packet, revise_packet, replace_plan, resolve_questions, answer_gate, add_unit, revise_unit, remove_unit, rebind_unit, set_dependencies.add_unit
packet_idNoCanonical packet identity returned by authoring; it identifies the bounded implementation work.
rationaleNoConcrete reasoning supporting this ordinary mutation, decision or selected authority. Applies to: start_packet, revise_packet.
work_planNoComplete ordered implementation plan with stable unit identities, dependencies, instructions and checks; accepted mutations give it authority. Applies to: replace_plan. Required by: replace_plan. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>).
depends_onNoExisting plan-unit identities this unit must consume before becoming executable. Applies to: set_dependencies. Required by: set_dependencies.
invariantsNoConditions that must remain true throughout the scoped behavior or change. Applies to: start_packet, revise_packet.
project_idYesCanonical lifecycle project ID. Select the existing project explicitly; development Markdown authorities are separate from runtime projects.
request_idYesCaller-owned retry identity. For receipted mutations replay the same actor and contents; changed contents can conflict. Inspect exact operation help for its receipt policy.
unit_patchNoExplicit patch to the identified existing plan unit; omitted fields preserve existing values under the ordinary revision rules. Applies to: revise_unit, rebind_unit. Required by: revise_unit, rebind_unit. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>).
finding_idsNoExisting assurance finding IDs that the corrective packet is intended to address. Applies to: start_packet.
milestone_idNoExisting milestone identity governing or filtering the requested scope. Applies to: start_packet.
out_of_scopeNoExplicitly excluded behavior and implementation work for this packet. Applies to: start_packet, revise_packet.
target_policyNoPacket target-selection policy controlling explicit/provider/materialization readiness requirements. Applies to: start_packet. Canonical values: code_targets_required, documental_only.code_targets_required
active_providerNoSelected implementation-provider identity for provider-owned packet execution. Applies to: start_packet.
client_unit_keyNoStable caller-owned unit identity used to reconcile authoring retries and locate the intended plan unit. Applies to: add_unit, revise_unit, remove_unit, rebind_unit, set_dependencies. Required by: revise_unit, remove_unit, rebind_unit, set_dependencies.
requirement_idsNoExplicit existing requirement IDs defining the selected scope. Applies to: start_packet, revise_packet.
source_revisionNoDeclared repository/source revision associated with the work or evidence; does not independently prove implementation. Applies to: start_packet.
gate_fingerprintNoFingerprint of the exact issued packet gate being answered; prevents responding to a different current gate. Applies to: answer_gate. Required by: answer_gate.
target_selectionNoStructured existing navigation/plan-unit target selection; inspect its current identities before binding. Applies to: add_unit.
architecture_refsNoReferences to components, interfaces or decisions in one adopted architecture revision; omission preserves selection and [] explicitly clears it. Applies to: start_packet, revise_packet.
completion_criteriaNoOrdered packet completion statements; these become stable criteria through the validation-authority workflow. Applies to: start_packet, revise_packet. Required by: start_packet.
unresolved_questionsNoKnown unresolved engineering/behavior questions retained on this packet; closure gates require resolution rather than anticipatory coding. Applies to: start_packet, revise_packet.
predecessor_packet_idNoExisting packet being superseded or corrected by this new packet. Applies to: start_packet.
required_campaign_idsNoExisting campaigns whose successful verification remains required by this corrective packet/finding. Applies to: start_packet.
expected_plan_revisionNoPlan revision issued with the work or gate being acted on; do not replace stale issued authority to legitimize old work. Applies to: revise_packet, replace_plan, resolve_questions, answer_gate, add_unit, revise_unit, remove_unit, rebind_unit, set_dependencies. Required by: revise_unit, remove_unit, rebind_unit, set_dependencies.
expected_spec_revisionNoPacket specification revision issued with the work or gate being acted on; mismatch rejects stale mutation. Applies to: revise_packet, replace_plan, resolve_questions, answer_gate, add_unit, revise_unit, remove_unit, rebind_unit, set_dependencies.
required_regression_evidenceNoDeclared regression evidence obligations that must remain visible until actually satisfied. Applies to: start_packet.
predecessor_dependency_policyNoDeclared dependency treatment when creating a successor/remediation packet. Applies to: start_packet. Canonical values: materialized, context_only.materialized

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed40 schema fields changedv0.5.1
    • addedInput schema / properties / active_provider / description
      Added value: +"Selected implementation-provider identity for provider-owned packet execution. Applies to: start_packet."
    • addedInput schema / properties / actor / description
      Added value: +"Identity of the human or agent recording this action; retain the original identity when replaying its request."
    • addedInput schema / properties / answers / description
      Added value: +"Structured resolutions of the packet's currently open engineering questions, using their issued identities. Applies to: replace_plan, resolve_questions. Required by: resolve_questions. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>)."
    • addedInput schema / properties / architecture_refs / description
      Added value: +"References to components, interfaces or decisions in one adopted architecture revision; omission preserves selection and [] explicitly clears it. Applies to: start_packet, revise_packet."
    • addedInput schema / properties / change_id / description
      Added value: +"Canonical owning change ID; when address resolution permits omission, the packet/campaign must resolve unambiguously."
    • addedInput schema / properties / client_unit_key / description
      Added value: +"Stable caller-owned unit identity used to reconcile authoring retries and locate the intended plan unit. Applies to: add_unit, revise_unit, remove_unit, rebind_unit, set_dependencies. Required by: revise_unit, remove_unit, rebind_unit, set_dependencies."
    • addedInput schema / properties / completion_criteria / description
      Added value: +"Ordered packet completion statements; these become stable criteria through the validation-authority workflow. Applies to: start_packet, revise_packet. Required by: start_packet."
    • addedInput schema / properties / depends_on / description
      Added value: +"Existing plan-unit identities this unit must consume before becoming executable. Applies to: set_dependencies. Required by: set_dependencies."
    • addedInput schema / properties / expected_plan_revision / description
      Added value: +"Plan revision issued with the work or gate being acted on; do not replace stale issued authority to legitimize old work. Applies to: revise_packet, replace_plan, resolve_questions, answer_gate, add_unit, revise_unit, remove_unit, rebind_unit, set_dependencies. Required by: revise_unit, remove_unit, rebind_unit, set_dependencies."
    • addedInput schema / properties / expected_spec_revision / description
      Added value: +"Packet specification revision issued with the work or gate being acted on; mismatch rejects stale mutation. Applies to: revise_packet, replace_plan, resolve_questions, answer_gate, add_unit, revise_unit, remove_unit, rebind_unit, set_dependencies."
    • addedInput schema / properties / finding_ids / description
      Added value: +"Existing assurance finding IDs that the corrective packet is intended to address. Applies to: start_packet."
    • addedInput schema / properties / gate_fingerprint / description
      Added value: +"Fingerprint of the exact issued packet gate being answered; prevents responding to a different current gate. Applies to: answer_gate. Required by: answer_gate."
    • addedInput schema / properties / goal_ids / description
      Added value: +"Existing goal graph IDs governing the packet or campaign scope. Applies to: start_packet, revise_packet."
    • addedInput schema / properties / in_scope / description
      Added value: +"Behaviors and implementation boundaries explicitly included in this packet. Applies to: start_packet, revise_packet."
    • addedInput schema / properties / intent / description
      Added value: +"Engineering statement of the packet's intended observable behavior and authorized scope. Applies to: start_packet, revise_packet. Required by: start_packet."
    • addedInput schema / properties / invariants / description
      Added value: +"Conditions that must remain true throughout the scoped behavior or change. Applies to: start_packet, revise_packet."
    • addedInput schema / properties / milestone_id / description
      Added value: +"Existing milestone identity governing or filtering the requested scope. Applies to: start_packet."
    • addedInput schema / properties / operation / description
      Added value: +"Operation selector for this multiplexer; use a canonical route listed below. Canonical values: start_packet, revise_packet, replace_plan, resolve_questions, answer_gate, add_unit, revise_unit, remove_unit, rebind_unit, set_dependencies."
    • addedInput schema / properties / operation / examples
      Added value: +[
      +  "start_packet"
      +]
    • addedInput schema / properties / out_of_scope / description
      Added value: +"Explicitly excluded behavior and implementation work for this packet. Applies to: start_packet, revise_packet."
    • addedInput schema / properties / packet_id / description
      Added value: +"Canonical packet identity returned by authoring; it identifies the bounded implementation work."
    • addedInput schema / properties / predecessor_dependency_policy / description
      Added value: +"Declared dependency treatment when creating a successor/remediation packet. Applies to: start_packet. Canonical values: materialized, context_only."
    • addedInput schema / properties / predecessor_packet_id / description
      Added value: +"Existing packet being superseded or corrected by this new packet. Applies to: start_packet."
    • addedInput schema / properties / project_id / description
      Added value: +"Canonical lifecycle project ID. Select the existing project explicitly; development Markdown authorities are separate from runtime projects."
    • addedInput schema / properties / purpose / description
      Added value: +"Canonical packet purpose, including ordinary implementation or governed semantic remediation. Applies to: start_packet. Required by: start_packet. Canonical values: implementation, remediation."
    • addedInput schema / properties / rationale / description
      Added value: +"Concrete reasoning supporting this ordinary mutation, decision or selected authority. Applies to: start_packet, revise_packet."
    • addedInput schema / properties / request_id / description
      Added value: +"Caller-owned retry identity. For receipted mutations replay the same actor and contents; changed contents can conflict. Inspect exact operation help for its receipt policy."
    • addedInput schema / properties / required_campaign_ids / description
      Added value: +"Existing campaigns whose successful verification remains required by this corrective packet/finding. Applies to: start_packet."
    • addedInput schema / properties / required_regression_evidence / description
      Added value: +"Declared regression evidence obligations that must remain visible until actually satisfied. Applies to: start_packet."
    • addedInput schema / properties / requirement_ids / description
      Added value: +"Explicit existing requirement IDs defining the selected scope. Applies to: start_packet, revise_packet."
    • addedInput schema / properties / response / description
      Added value: +"Structured answer to the issued packet gate; use its current fingerprint and exact response contract. Applies to: answer_gate. Required by: answer_gate. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>)."
    • addedInput schema / properties / source_revision / description
      Added value: +"Declared repository/source revision associated with the work or evidence; does not independently prove implementation. Applies to: start_packet."
    • addedInput schema / properties / target_policy / description
      Added value: +"Packet target-selection policy controlling explicit/provider/materialization readiness requirements. Applies to: start_packet. Canonical values: code_targets_required, documental_only."
    • addedInput schema / properties / target_selection / description
      Added value: +"Structured existing navigation/plan-unit target selection; inspect its current identities before binding. Applies to: add_unit."
    • addedInput schema / properties / title / description
      Added value: +"Short human-readable title of the authored requirement, finding, packet, run step or campaign. Applies to: start_packet, revise_packet. Required by: start_packet."
    • addedInput schema / properties / unit / description
      Added value: +"Complete bounded implementation-unit declaration, including instructions, targets, producer/consumer contracts and verification obligations as required by plan authority. Applies to: add_unit. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>)."
    • addedInput schema / properties / unit / examples
      Added value: +[
      +  {
      +    "client_unit_key": "supporting-module",
      +    "file_path": "src/supporting_module.py",
      +    "instructions": [
      +      "Create the bounded supporting module.",
      +      "Export the contract required by its declared consumers."
      +    ],
      +    "operation_kind": "new_file",
      +    "unit_checks": [
      +      "The required public contract is exported."
      +    ]
      +  }
      +]
    • addedInput schema / properties / unit_patch / description
      Added value: +"Explicit patch to the identified existing plan unit; omitted fields preserve existing values under the ordinary revision rules. Applies to: revise_unit, rebind_unit. Required by: revise_unit, rebind_unit. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>)."
    • addedInput schema / properties / unresolved_questions / description
      Added value: +"Known unresolved engineering/behavior questions retained on this packet; closure gates require resolution rather than anticipatory coding. Applies to: start_packet, revise_packet."
    • addedInput schema / properties / work_plan / description
      Added value: +"Complete ordered implementation plan with stable unit identities, dependencies, instructions and checks; accepted mutations give it authority. Applies to: replace_plan. Required by: replace_plan. Exact required/optional dotted fields and guidance: fow_capabilities(view=operation, operation_tool=fow_packet_author, operation_name=<selected route>)."
  2. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true, so the safety profile is covered. The description meaningfully adds: removal/replacement changes current plan authority, provider-target deltas may be queued, and — importantly — no coding work is actually executed. That is real context beyond the structured hints.

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?

Four labeled lines (purpose, routing, prerequisites, effects, help) front-load the definition and are scannable. Given a 38-parameter multiplexer, the density is justified, though the help-pointer sentence and some phrasing are slightly redundant with the schema's own capability notes.

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?

With an output schema present, return values need not be described, and the description still covers effects, prerequisites, routing, and where to get per-operation detail. For a tool of this complexity it is nearly complete; only the when-versus-siblings dimension is left implicit.

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% across 38 parameters, so the schema already documents each field's meaning and applicable operations. The description adds only the operation-route enumeration and a pointer to fow_capabilities for exact dotted-field help, which does not meaningfully exceed the schema's own content. 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?

States a specific verb and resource — defining bounded implementation work in a packet — and enumerates what that entails (instructions, stable plan units, dependencies, producer/consumer contracts, checks). The operation list makes the tool's surface très concrete. It doesn't explicitly name a sibling such as fow_packet_advance or fow_packet_inspect to disambiguate, so it falls short of a 5.

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?

"Route with operation: ..." tells how to select a mode, and the Prerequisites line gives a precondition (use current spec/plan revisions, close semantic gaps before dispatch). However, nothing says when to choose this authoring tool over fow_packet_advance or fow_packet_inspect, so guidance is implied rather than explicit.

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