mc_task

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

With no annotations, the description carries the full burden. It does disclose genuinely useful behavior: persistence to tasks.json and survival across reconnect, plus that run advances one step per round. It omits critical traits — notably that steps contain `op`/`args` tool invocations, so run appears to execute other tools; there is no disclosure of failure handling, the meaning of force, or whether any step is destructive.

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 compact sentences, front-loaded with what the resource is and where it lives, then the action glosses. No filler. The telegraphic style borders on under-specification for a 9-parameter, 11-action tool, but the ordering and density are good.

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 tool with 9 parameters, 11 distinct actions, no annotations, and no output schema, the description covers only 4 actions and never explains what a run actually does or what a task record looks like. An agent could not reliably pick done vs cancel vs forget, or predict run's side effects, from this text alone.

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 100%, so the baseline is 3, but the description adds real meaning the schema does not: run advances one step per round, resume re-verifies, plan/step do bookkeeping. That clarifies enum values a schema alone leaves as bare strings. It still leaves list/get/note/done/cancel/forget and the force/limit interactions unexplained.

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 concrete verb+resource pair: a persistent progress ledger for long tasks, with storage location (tasks.json under the memory root) and lifetime (survives disconnect/reconnect). It also names four of the actions (run/resume/plan/step). It does not differentiate itself from nearby siblings such as mc_sequence or mc_auto, which an agent could plausibly confuse with task orchestration.

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?

"Long task auto-created when digging more than 4 blocks" implies when the ledger exists, and run/resume/plan/step get one-phrase roles. But there is no statement of when to choose this over mc_sequence/mc_auto, no precondition for run, and 7 of the 11 actions (list, get, note, done, cancel, forget) receive no guidance at all.

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