autocorrect_simulation

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

With no annotations provided, the description carries the full behavioral burden, and it does disclose the critical traits: it mutates the input deck ('editing the deck'), runs an external solver, retries up to max_iters, and returns a narrative. The main gap is that it does not say whether the original deck is backed up, modified in place only, or left in its fixed state afterward — notable for a file-mutating tool.

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 description is front-loaded with the core purpose, adds the return behavior in one sentence, and then presents a clean Args block. Every sentence earns its place — the parameter documentation is necessary precisely because the schema has 0% coverage. There is no redundant or filler text.

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 0% schema coverage, the description covers purpose, all parameter semantics, the return narrative, and the key side effect. An output schema exists, so return details need not be spelled out. The remaining gaps are modest: no rollback/backup behavior, no guidance on what happens when max_iters is exhausted, and no explicit routing against sibling tools.

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%, so the description must compensate, and it fully does: the Args block adds real meaning to all five parameters — inp_path gets its file format, job_name gets its defaulting behavior, max_iters gets its scope, cpus gets its purpose, and timeout_s gets its unit and per-run scope. Every parameter is documented beyond what the bare schema provides.

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 specific verb-resource pairing ('Run a job and autonomously fix failures... by editing the deck') and names concrete failure types (convergence, singularity, deck errors) plus the diagnostics sources (.sta/.msg/.dat). This clearly distinguishes it from siblings like run_simulation (plain run), apply_reasoned_fix (single fix), and get_fix_log (read-only log), so an agent can tell them apart without opening schemas.

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?

The intended use is implied — call this when you want an autonomous run/fix loop with retries — but the description never explicitly says when to prefer it over run_simulation or apply_reasoned_fix, nor does it state exclusions (e.g., 'use run_simulation if you do not want the deck modified'). Guidance is inferable from the purpose statement but not made explicit.

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