Skip to main content
Glama

Planner — provable "done" for AI agents

by com.monopoly-gold.planner

project-remove-dependency

Idempotent

Remove a project dependency. Two lookup modes: pass dependency_id (UUID of the link itself), or pass both projectId and dependsOnProjectId (UUID or slug). Returns removed=true on success, removed=false if the dependency was not found.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectIdNoUUID или slug проекта-зависимого (если dependencyId не задан)
dependencyIdNoUUID самой связи
dependsOnProjectIdNoUUID или slug целевого проекта (если dependencyId не задан)

TDQS

A4.2/5.0
Behavior4/5

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

Beyond annotations (idempotentHint=true, readOnlyHint=false), the description discloses the return behavior (removed=true/false), aligning with idempotency. No contradiction with 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?

Two well-structured sentences: purpose first, then modes and return value. No redundant information.

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?

The description explains both modes and return values, sufficient for a simple removal tool. Lacks details on error cases, but annotations cover idempotency.

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?

With 100% schema coverage, the description still adds value by grouping parameters into two lookup modes and clarifying UUID/slug usage, going beyond the schema's individual descriptions.

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?

The description clearly states 'Remove a project dependency' and explains two lookup modes, distinguishing it from siblings like 'project-add-dependency'.

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?

The description describes two modes but does not provide explicit guidance on when to use each or when not to use this tool versus alternatives.

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

All Planner — provable "done" for AI agents toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation2/5

The evidence and attachment tools are hard to tell apart by name: goal-attach-evidence, goal-add-evidence-text, goal-attach-file, and goal-request-upload all sound like "put evidence on a goal," and only very long descriptions separate AC-covering bytes from non-covering text notes from goal-level attachments from an alternate upload transport. goal-create vs goal-todo and goal-suggest-assumptions vs goal-add-assumption add further boundary confusion.

Naming Consistency4/5

Most tools follow a clear verb_noun pattern with goal- or project- prefixes (goal-create, goal-update, project-delete, project-add-dependency). Minor deviations like account-delete (noun-verb), goal-summary/goal-tree/goal-todo (nouns), and goal-recent-unresolved break the pattern slightly, and add vs attach is used inconsistently within the evidence family.

Tool Count2/5

39 tools is far past the 25+ threshold for "too many" and will force agents to navigate a very large surface. While the domain is broad, much of the count comes from fine-grained goal sub-resources (evidence, criteria, assumptions, blockers, notes, escalations) that could have been consolidated.

Completeness5/5

The tool surface covers the full lifecycle: project CRUD and dependencies, goal creation/update/delete/move/reorder/tree, acceptance criteria with evidence gates, assumptions with evidence-based statuses, blockers, notes, escalations, red-team dismissal, and aggregate stats. There are no obvious dead ends for the stated planning-and-proof workflow.

Resources