sqo_spec_engine

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

With no annotations supplied, the description carries the full burden, and it does disclose real behavior: state persists in `.sqo/specs.db`, tasks are atomic with file-ownership locks, briefs are capped at <220 tokens, and completion is gated by verification commands. What it omits is equally important — whether `complete` mutates or destroys state, what happens on a failed verification gate, and what permission or ordering constraints apply across actions.

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?

It is a single compact sentence with no filler, and the concrete behaviors are packed in. But it is front-loaded with branding ('Spec-Kit + Taskmaster Autonomous Spec-Driven DAG Engine (v10.0)') that conveys nothing operational and pushes the useful content to the back.

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 7-parameter tool with a four-value action enum, no annotations, and no output schema, the description leaves the core lifecycle unexplained: it never describes what `init`, `next`, `complete`, or `status` each do, nor the relationship between `workspace`, `slug`, and `step_key`. An agent would have to guess at the action sequence and at what a call returns.

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 schema already documents all 7 parameters and the `action` enum values. The description adds only marginal meaning, mainly the <220-token size of a `next` brief and the notion of verification gates around `complete`. Baseline 3 applies since the schema does the heavy lifting.

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 names a specific resource (`.sqo/specs.db` atomic task graphs) and states behaviors like file-ownership locks and token-budgeted `next` briefs. However, it never plainly says this is a spec-lifecycle state machine with init/next/complete/status actions, and it does nothing to distinguish itself from the many sibling `sqo_*` tools. An agent gets the domain but not the concrete operation.

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?

There is no when-to-use, when-not-to-use, or alternative guidance at all. The mention of '`next` task briefs' hints that `next` is a retrieval step, but the description never explains when an agent should call this tool versus, say, `sqo_context_pack` or `sqo_checkpoint`, nor when to prefer `status` over `next`.

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