Skip to main content
Glama

add_dependency

Creates a dependency edge so a task waits for a blocker, with default blocks behavior holding the dependent task until the blocker is done; relates_to and is_child_of only record links.

Instructions

Add a dependency edge: task_id depends on depends_on_task_id. With the default type blocks, task_id is held back from its assignee until the blocker meets condition (default: the blocker is done). relates_to and is_child_of only record a link and hold nothing. Change the condition with update_dependency; delete the edge with remove_dependency.

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": {
      "task_id": "<task_id>",
      "depends_on_task_id": "<depends_on_task_id>"
    },
    "name": "add_dependency"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYesUUID of the dependent task: the one that waits.
conditionNoWhat a blocks edge waits for. task_done (default): the blocker reaches done or cancelled. access_ready / contract_ready / artifact_published: released by evidence_url, or when the blocker reaches done or cancelled. shipped: the blocker is marked shipped or reaches done (cancelled does not release it). deployed: the blocker is marked shipped or a VCS link of it has a recorded deploy (see mark_vcs_deployed); merged/done alone does not release it. accepted: the blocker reaches done (cancelled does not release it). Evidence (evidence_url) releases an edge of any condition. Only for blocks edges. Use a non-default condition when the blocker is a perpetual monitor/recurring card that never reaches done. The response carries `warning` when a blocks edge targets such a card, and `condition_satisfied` (true when the edge no longer holds the dependent).
evidence_urlNoProof that the condition already holds (link to the artifact, check or comment). With a non-task_done condition it releases the edge at once; otherwise set it later with update_dependency.
dependency_typeNoDependency type: blocks, relates_to, is_child_of.blocks
depends_on_task_idYesUUID of the blocker: the task that must be done (or meet condition) first. Must differ from task_id. Direction matters; swapping the two makes the blocker wait instead.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.6
    • addedInput schema / properties / condition
      Added value: +{
      +  "description": "What a blocks edge waits for. task_done (default): the blocker reaches done or cancelled. access_ready / contract_ready / artifact_published: released by evidence_url, or when the blocker reaches done or cancelled. shipped: the blocker is marked shipped or reaches done (cancelled does not release it). deployed: the blocker is marked shipped or a VCS link of it has a recorded deploy (see mark_vcs_deployed); merged/done alone does not release it. accepted: the blocker reaches done (cancelled does not release it). Evidence (evidence_url) releases an edge of any condition. Only for blocks edges. Use a non-default condition when the blocker is a perpetual monitor/recurring card that never reaches done. The response carries `warning` when a blocks edge targets such a card, and `condition_satisfied` (true when the edge no longer holds the dependent).",
      +  "enum": [
      +    "task_done",
      +    "access_ready",
      +    "contract_ready",
      +    "artifact_published",
      +    "shipped",
      +    "deployed",
      +    "accepted"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / depends_on_task_id / description
      Previous value: -"ID of the task this depends on."New value: +"UUID of the blocker: the task that must be done (or meet condition) first. Must differ from task_id. Direction matters; swapping the two makes the blocker wait instead."
    • addedInput schema / properties / evidence_url
      Added value: +{
      +  "description": "Proof that the condition already holds (link to the artifact, check or comment). With a non-task_done condition it releases the edge at once; otherwise set it later with update_dependency.",
      +  "type": "string"
      +}
    • changedInput schema / properties / task_id / description
      Previous value: -"Task ID."New value: +"UUID of the dependent task: the one that waits."
  2. First observedv0.1.1

TDQS

A4.7/5.0
Behavior5/5

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

Annotations declare only that this is a non-idempotent, non-destructive write. The description goes well beyond that: it explains the actual consequence (the dependent is held back from its assignee until the blocker meets the condition), what each condition releases on, that evidence_url releases an edge of any condition, and that responses carry `warning` and `condition_satisfied`. That is real context an agent could not derive from 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.

Conciseness5/5

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

Four sentences, front-loaded with the direction and the default behavior, then the non-holding edge types, then the sibling routing. No restatement of the tool name and no filler; every clause either defines effect or dispatches the agent elsewhere.

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

Completeness5/5

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

No output schema exists, and the description still covers the effect of the write, the condition matrix, the evidence short-circuit, and the response fields that matter (`warning`, `condition_satisfied`). For a 5-parameter dependency mutation this is sufficient to invoke correctly.

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 and the schema already carries the heavy detail on conditions and evidence. The description adds the framing that 'blocks' is the type the condition applies to and that the two task IDs are direction-sensitive ('swapping the two makes the blocker wait instead'), which is meaningful beyond the schema's per-field notes.

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?

Opens with a specific verb and resource plus the direction semantics: 'Add a dependency edge: task_id depends on depends_on_task_id.' It immediately distinguishes the edge types by effect (blocks holds back work; relates_to/is_child_of only record a link), so an agent can tell what it is creating 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?

Explicitly routes modification and deletion to update_dependency and remove_dependency, and explains the release condition per edge type so the agent can pick a type deliberately. It stops short of covering the creation-side alternatives — notably when to use an is_child_of edge versus the sibling create_subtask, and no guidance on cycles beyond the schema's 'must differ from task_id'.

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