deepseek_chat

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must cover behavioral traits on its own. It discloses modes and DeepThink support, but omits output format, conversation continuity defaults, and the fact that smartSearch is quick-mode-only (which is only in the schema).

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 tightly written sentences; the main action is front-loaded and the mode summary earns its place. No filler.

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?

The description plus schema cover the input space, but there is no output schema and no mention of what the response looks like. It also doesn't route the agent to specialized siblings, so a user needing code review might still pick this tool.

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 100%, so the baseline is 3. The description mostly restates the mode enum and adds the 'with search+upload' capability, but it doesn't clarify any parameter beyond what the schema already documents.

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 clear verb and resource: 'Send a prompt to DeepSeek and return the AI response.' It does not explicitly contrast with sibling tools like deepseek_code_review or deepseek_debug, so it falls short of a full 5, but the general-purpose intent is unmistakable.

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 mode descriptions imply use cases (quick for default, expert for reasoning, vision for image analysis), but there is no explicit guidance about when to choose this general chat tool versus the specialized deepseek_* siblings, nor any exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.