agent_start_task

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

With no annotations, the description carries the full burden and does disclose meaningful mutation behavior: it creates a working-memory file and mutates an active-task.md pointer, plus what it returns. It stops short of noting permissions, overwrite semantics if a task already exists, or failure modes.

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, zero waste, side effects and return values front-loaded after the purpose statement. Nothing could be cut without losing information.

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 mutation tool with no annotations and no output schema, the description supplies the key behavioral facts (files created, pointer set, taskId/paths returned) an agent needs before invoking it. Missing only prerequisite/error handling detail, which is minor here.

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 all four parameters (including optional project, task_id override, and description) are already documented in the schema. The description adds no parameter-level meaning, so the baseline of 3 applies.

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+resource ('Start a new task for an agent') and names the concrete side effects (working-memory file, active-task.md pointer) and return values. It implicitly contrasts with siblings like close_agent_task and agent_abandon_task, but never names them explicitly.

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?

Usage context is implied — you call this before doing task work — but there is no explicit when/when-not guidance and no mention of alternatives such as agent_active_task or close_agent_task. Adequate minimum without routing help.

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