deepseek_routing

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

With no annotations, the description must carry the full behavioral burden. It does signal a read/write duality and a user-consent guardrail, but omits key mutation semantics: whether the set/effort/models objects merge with or replace existing values, whether changes are reversible, and what permissions are needed.

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?

A single tight sentence, front-loading the show/change duality followed by the scope of what is configured and the consent constraint. 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?

For a 5-parameter mutation tool with nested objects, no annotations, and no output schema, the description leaves meaningful gaps: partial-update/merge behavior and the purpose of 'workspace' are unexplained, and the return shape is unspecified (excusable in the absence of an output schema, but the write semantics still matter).

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 80%, so baseline is 3; the schema already explains set, scope, effort, and models with examples. The description adds only '(the user's choice)' framing and says nothing about the undocumented 'workspace' parameter, so it does not improve on the 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?

States specific verbs (show/change) and a concrete resource: per-task-type agent routing, default DeepSeek model, and thinking effort. An agent can immediately tell this is a configuration-inspection/mutation tool, though it does not explicitly contrast itself with siblings like deepseek_task or deepseek_ask.

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?

'Only change it when the user asks' is an explicit when-not guardrail for the write path, with the read path implied by 'Show'. There is no positive guidance on when to prefer this over deepseek_task or how it relates to per-request routing, but the mutation constraint is clearly stated.

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