check_run_health

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

With no annotations, the description carries the full behavioral burden and does so: it defines every possible verdict value, warns that `ok: true` only means the files were read, and discloses the staleness heuristic ('staleness is judged by file times: run each job in a clean folder'). These are precisely the non-obvious traits an agent needs before trusting the result.

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 core action is front-loaded in the first sentence and the verdict list is dense but each item earns its place by enabling correct interpretation. The long enumerated verdict parenthetical is the only mildly heavy section, though it is arguably necessary for a multi-outcome tool.

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?

An output schema exists, so return values need not be spelled out, yet the description still supplies verdict semantics and caveats that make the output actionable. Remaining gaps are minor — e.g., which files are mandatory vs optional, or what happens when energy files are missing alongside the d3hsp.

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 does: hourglass_limit is defined as 'max hourglass/internal, default 0.10', balance_tol as 'allowed deviation of the energy ratio from 1', and quasi_static gets its rule of thumb (kinetic energy above 5% of total). Only `directory` is left unexplained, though it is self-evident.

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 states a specific verb and resource ('Judge a run from glstat (or binout) and d3hsp') and enumerates the exact checks performed (termination, energy balance, hourglass, negative sliding energy, kinetic energy). Its verdict-aggregation role clearly distinguishes it from siblings like read_glstat, read_binout, or get_run_progress, which only surface raw data.

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 clear context for when the tool is intended (judging a run's health, with `quasi_static` and staleness caveats) and explains what each verdict means. It stops short of explicitly naming alternatives (e.g., 'use read_glstat for raw series data') or stating when not to use it.

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