Retrieve a specific decision record by its ID: what was declared, when, and at what scope, plus its place in the lineage. Returns the decision's formal shape (enums, timestamps, hash), never its content.
| Name | Required | Description | Default |
|---|---|---|---|
| dd_id | Yes | The DD ID to retrieve | |
| auth_token | Yes | Your DA agent auth token |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It explicitly states what is NOT returned ('never its content'), which is a valuable behavioral detail. It also mentions return components (enums, timestamps, hash) without needing to describe format. This is good transparency for a read operation, though not exhaustive.
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?
Two sentences, front-loaded with the purpose, and no wasted words. Every clause adds information: what, when, scope, lineage, formal shape, and explicit exclusion of content. Perfectly concise for the information density.
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 tool with 2 params and no output schema, the description is effective. It explains what the output contains (declared, when, scope, lineage, formal shape) without a schema. It could mention error cases or auth requirements, but auth_token param covers auth. Given the tool's simplicity, it's quite 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 covers 100% of parameters, and dd_id is described simply as 'The DD ID to retrieve'. The description adds context about the ID being a 'specific decision record' and hints at lineage, which adds slight value. With full schema coverage, this is a solid 4, as the description goes a bit beyond the bare schema.
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?
Clearly states the tool retrieves a specific decision record by ID, describes what it returns (declaration, timing, scope, lineage, formal shape), and distinguishes from siblings like list_decisions and get_decision_metadata_distribution. The verb 'retrieve' combined with specific resource and scope is precise.
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 implies a lookup-by-ID use case, which is clear context. However, it doesn't explicitly state when not to use it or mention alternatives like list_decisions for browsing. Maybe there is no explicit exclusion, but the purpose statement makes the usage obvious, so a 4 is fair.
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, but a few overlap in function: get_decision_metadata_distribution and get_self_classification_distribution are both distribution getters, and observe_environment and observe_pattern could be confused. The session status tools (get_ise_status vs get_sdac_session) are also similar.
All tool names follow a consistent snake_case verb_noun pattern (create_, get_, list_, observe_, run_, end_, exit_, confirm_, etc.). There are no stylistic deviations or mixed conventions.
With 30 tools, the surface is heavy. Several tools could be consolidated (e.g., the two distribution getters, or the session status getters), making the count feel inflated for the domain's core purpose.
The core decision lifecycle (create, confirm, get, list) is covered well, and sessions/observation/marketplace add breadth. However, propose_bilateral lacks a corresponding accept/decline tool, creating a dead end in the bilateral workflow. Also, no way to fetch detailed info on a specific marketplace tool.