LLM generates suggested assumptions for a goal edge (parent→child). Returns 2-4 assumptions with signposts and type classification. Author should review, edit, and accept relevant ones via goal-add-assumption.
| Name | Required | Description | Default |
|---|---|---|---|
| goalId | Yes | UUID цели (ребёнка) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the read-only and idempotent annotations, the description discloses that the output is LLM-generated, includes 2-4 assumptions with signposts and type classification, and requires author review/editing before acceptance. This adds important behavioral context not captured by 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with purpose, then output format, then next-step guidance. Every sentence earns its place with no redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only suggestion tool with one parameter, full schema coverage, and annotations, the description is complete. It explains what it returns (2-4 assumptions with signposts and type classification) and the required human-in-the-loop workflow, so the agent can determine when and how to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already fully describes the only parameter (goalId with description 'UUID цели (ребёнка)'). The description adds no new information about the parameter itself; the parent→child context is already contained in the schema's 'ребёнка' (child) note. Thus the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action: 'LLM generates suggested assumptions for a goal edge (parent→child).' It clearly identifies the resource (assumptions for a goal edge) and distinguishes itself from sibling tools like goal-add-assumption, which actually adds assumptions rather than suggesting them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear workflow context: 'Author should review, edit, and accept relevant ones via goal-add-assumption.' This tells the agent that this tool is for generation, and the follow-up action belongs to a different tool. However, it does not explicitly state when not to use this tool or compare it to other alternatives like goal-update-assumption.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clear distinct purposes (goal-create vs goal-update vs goal-delete), but the evidence-related tools (goal-add-evidence-text, goal-attach-evidence, goal-request-upload) and note tools (goal-add-note) have overlapping concepts that require careful reading of descriptions to differentiate. Overall, the detailed descriptions help resolve ambiguity, but a few tools could be easily confused.
The majority follow a consistent verb_noun pattern with a resource prefix (goal-create, goal-get, project-list, project-update). However, there are deviations like account-delete (noun-verb reversed), goal-todo, goal-summary, goal-tree, and goal-recent-unresolved that break the pattern. The inconsistency is minor but noticeable.
With 38 tools, this server has a very large surface area. Even for a complex planner with evidence management, the number exceeds the 25-tool threshold for 'too many'. Many tools could potentially be consolidated (e.g., goal-add-note and goal-add-evidence-text), and the size may overwhelm agents during tool selection.
The tool set provides complete coverage of the domain: full goal lifecycle (create, get, update, delete, list, tree, move, reorder, block), evidence management (attach, request upload, text evidence, remove), acceptance criteria (add, update, remove, request change, resolve escalation), assumptions (add, update, remove, suggest, attach evidence), blockers, notes, project management (CRUD, dependencies), and configuration settings. No critical gaps are apparent.