get_annotation_analysisRead the latest stored AI diagnosis for an annotation (root causes, confidence, suggested fix, and likely source files). Returns null when none has been generated yet; run diagnose_annotation to create one.
| Name | Required | Description | Default |
|---|---|---|---|
| annotation_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| analysis | No | ||
| diagnosis_enabled | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and non-destructive. The description adds valuable context: that the tool returns null if no diagnosis exists and that it reads the latest stored diagnosis, without contradicting 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 consists of two sentences, front-loading the key action and listing what the diagnosis includes. Every sentence adds value, and 'run diagnose_annotation' provides a clear next action. No wasted words.
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?
Given the output schema exists, the description does not need to detail return values. It covers the core behavior (read diagnosis, null case), differentiates from the sibling tool, and handles the parameter sufficiency. The tool is simple and the description is complete.
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?
Schema description coverage is 0%, so the description should compensate. However, the single required parameter 'annotation_id' is self-explanatory from the context. The description does not explicitly explain it but the name and tool purpose make it clear, so it is adequate.
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 clearly states it reads the latest stored AI diagnosis for an annotation, listing specific fields (root causes, confidence, suggested fix, source files). It distinguishes itself from the sibling tool 'diagnose_annotation' which creates the diagnosis.
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 explicitly says when to use this tool (to read a diagnosis) and provides an alternative: 'run diagnose_annotation to create one'. It also clarifies behavior when no diagnosis exists (returns null).
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.
Each tool targets a distinct aspect of annotation or project management. Complementing pairs like diagnose_annotation vs. generate_prompt and get_annotation_analysis vs. diagnose_annotation are clearly differentiated by descriptions. No two tools overlap in purpose.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., list_annotations, create_github_issue, get_activity). Verbs like get, list, create, add, update are used systematically, ensuring predictability.
With 17 tools, the server covers annotation operations, project metrics, comments, GitHub integration, and sharing without being overwhelming. The scope is well-scoped for a specialized feedback/annotation tool.
Core annotation workflows (list, get, update status, comment, diagnose, generate prompt, create issues) are covered. Missing annotation creation, deletion, and detail updates are minor gaps given the server's focus on post-creation analysis and workflow.