Ask DeepSeek a one-shot question for a cheap second opinion, optionally including file paths for context. Use when you need a quick answer without tool execution.
One-shot question to DeepSeek, no tools (cheap second opinion). Routed as type 'question'. Pass file paths to include them.
| Name | Required | Description | Default |
|---|---|---|---|
| files | No | Files whose contents DeepSeek should see | |
| model | No | ||
| question | Yes | ||
| workspace | No | ||
| user_override | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description does carry real behavioral weight: it discloses single-shot semantics, no tool use, cheapness, and that the call is routed as type 'question'. It does not say whether the call blocks, what permissions or approval flow apply (relevant to user_override), or what the response looks like.
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?
Three short sentences, front-loaded with purpose before implementation detail. 'Routed as type question' is arguably internal plumbing, but it is plausibly useful for downstream report lookups; nothing else is wasted.
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 5-parameter tool with no annotations, no output schema, and 20% schema description coverage, the definition leaves too much unstated: default model, workspace scoping, the meaning/effect of user_override, and whether results are returned inline or via deepseek_get_report.
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?
Only 1 of 5 parameters is explained anywhere ('Pass file paths to include them', matching the files array); schema coverage is 20%. The model enum, workspace, and especially user_override (a boolean defaulting to false, likely a safety/approval gate) are opaque in both schema and description.
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?
States a specific verb and resource (one-shot question to DeepSeek) plus the key scope constraint 'no tools'. The '(cheap second opinion)' framing and 'no tools' implicitly contrast with the heavier sibling deepseek_task, though it never names that sibling.
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?
'Cheap second opinion' and 'no tools' imply the use case (quick, single-turn, tool-free queries), but there is no explicit 'use X instead when...' guidance naming deepseek_task or deepseek_routing, and no stated exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.