ispw_generate_assignment

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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new signals: the operation is asynchronous and returns an operation ID plus a status URL for polling — an important behavioral detail absent from annotations. It does not say whether generation can fail mid-run or what happens to prior generated output.

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?

The prose lead and the Returns/Examples blocks earn their place, but the Args section duplicates the schema field-for-field with identical wording, spending a third of the description on zero-information repetition. The useful content is front-loaded, so the structural ordering is sound.

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?

With an output schema present, the return description is a bonus rather than a necessity, and the async status-URL note is the key missing-from-schema fact an agent needs. Coverage of the workflow position and example invocations rounds it out; the gap is that the ambiguous optional parameters (level, runtime_configuration) remain unexplained.

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 0% and the description merely restates the schema verbatim ("srid: System Resource Identifier", "level: Target level for generation"), adding no meaning — it never explains what an SRID value looks like or what a "level" such as DEV implies. The examples contribute the only real value by showing concrete values (srid="ISPW", level="DEV"), which is useful but thin compensation for a 0% coverage gap.

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 and resource ("Generate code for an ISPW assignment") and expands it into concrete mechanics: compiles and prepares code within an assignment. It also places the action in the workflow — first step after code changes, before promoting to higher environments — which implicitly separates it from ispw_promote_assignment and ispw_deploy.

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?

"This is typically the first step after code changes before promoting to higher environments" gives a clear when-to-use context and names the subsequent step, letting an agent infer that promote/deploy are downstream. It stops short of explicit exclusions or prerequisites (e.g., what states an assignment must be in to be generated).

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