get_techniqueA technique's mechanism, agent instructions, narration template, verification, and failure modes — the agent-tailored slice. The full human page is linked, not inlined.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Technique id, e.g. from classify_intent or find_technique |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It reveals that the tool returns a subset (agent-tailored) and links the full human page, indicating partial data. However, it does not disclose potential side effects, auth requirements, rate limits, or behavior on invalid IDs, leaving gaps for a retrieval operation.
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 efficiently convey the tool's purpose and scope. Every sentence adds value: the first enumerates return fields, the second clarifies the agent-oriented nature and links. No redundancy or waste.
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?
Although there is no output schema, the description lists five specific return categories (mechanism, instructions, etc.), providing a solid understanding of the response. It could mention additional details like potential empty results or error handling, but for a retrieval tool it is reasonably 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?
The single parameter 'id' is fully described in the schema as a technique ID from other tools. The description adds no new semantic detail beyond what the schema provides. Since schema coverage is 100%, a score of 3 is appropriate.
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 retrieves a technique's mechanism, instructions, narration template, verification, and failure modes. It distinguishes itself from siblings by specifying it returns an 'agent-tailored slice' and mentions the full human page is linked, clarifying its scope.
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?
No explicit guidance on when to use this tool versus alternatives like 'find_technique' or 'classify_intent'. The description does not specify prerequisites or exclusion criteria, leaving the agent to infer usage context from sibling names alone.
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 has a distinct purpose: listing categories, classifying intent, finding/getting technique details, and applying a technique. There is no overlap, and descriptions clearly differentiate them.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., apply_technique, list_categories). The naming is uniform and predictable.
With 5 tools, the server is well-scoped for its focus on technique selection and application. Each tool serves a necessary step in the workflow without unnecessary bloat.
The tool surface covers the full workflow: browsing categories, classifying intent, retrieving technique details, and applying techniques. There are no obvious gaps for an agent using this server.