ddflow_job_add

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

With no annotations, the description carries the full behavioral burden. It adds real context — registration is for live processes and liveness is checkable by anyone, even after pid reuse — but omits error/idempotency behavior and what happens if the same pid is registered twice.

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, front-loaded sentence that conveys the core action and scope without filler. The trailing aside about pid reuse is somewhat parenthetical but earns its place.

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 no annotations and no output schema, the description covers what the tool does but not what it returns (e.g., a job handle/id) or how the registered job is later consumed by ddflow_job_list / ddflow_job_end. Adequate but with clear gaps.

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 five parameters are already documented in the schema. The description only reiterates that pid is the key and adds nothing about item, command, log, or as_agent semantics. Baseline 3 is appropriate.

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 uses a precise verb ('register'), names the resource (a long-running process), and specifies the identifying key (by pid) plus the intended source (processes started via torchrun or a launcher script). This clearly separates it from siblings like ddflow_job_run, which presumably launches a process itself.

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?

It gives a clear condition for use: you already started the process some other way and want it registered while it runs, so liveness can be checked later. It implies but does not explicitly name the contrast with ddflow_job_run / ddflow_job_end, so routing is inferable rather than stated.

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