deepseek_task

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

With no annotations, the description carries the burden and does well: it discloses the agent's autonomy ("reads/writes files, runs tests, works until done"), cost posture ("cheap subagent"), token-budget mechanics, and the read_only defaults per type. Gaps remain on the approval path — siblings list_pending_approvals/approve_actions suggest gated writes, and the terse "`ask` = ask the user first" is not explained (the type enum has no "ask" value).

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?

Front-loaded with the core action, then the routing table in compressed arrow form — efficient for the amount of decision content. Slight deductions for the cryptic "`ask` = ask the user first" fragment, which references a value not in the enum and costs a sentence without resolving anything.

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 14-parameter, annotation-free, no-output-schema tool, the description covers the decision-critical material: routing, cost, autonomy, parallelization, and default resolution. It stops short on the approval workflow and on detail/max_steps/context_globs, which the schema only partly documents.

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 coverage is 79%, so the baseline is 3; the description adds real meaning beyond it — model omission semantics ("Omit model to use the user's default"), the "Give file paths, not contents" constraint on files, and the parallelization semantics of areas ("parallel sub-tasks with one merged report"). Unexplained params remain (detail, max_steps, context_globs) but are minor.

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?

Specific verb+resource with capability detail: "Hand a task to DeepSeek (cheap subagent; reads/writes files, runs tests, works until done)". It also states the return shape ("Returns a compact report"). It differentiates against the claude-side alternative through the routing table, though it does not distinguish itself from sibling deepseek_ask (likely a conversational variant).

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?

Explicit when-to-use routing table (plan→claude, code→deepseek, ... other→claude), an explicit exclusion ("Only use for types routed to deepseek"), and an escape hatch ("or when the user explicitly asked for DeepSeek (set user_override)"). It even names deepseek_routing for the default-model question. Nothing about selection is left to inference.

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