cht_channel_submit

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

With no annotations, the description carries the full burden and does so richly: asynchronous execution, an explicit degradation contract instead of a raise, the job_id/status/cache_hit return shape, the required polling step, and expected ranges for the physics gates (energy_balance_ratio ≈1 ±3%, solid_drop_ratio ≈1). It even discloses a known modeling failure mode (stabilized advection leaking the energy balance above Pe 25).

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?

Front-loaded with the definition, then risk/behavior, then returns — a sensible ordering. It is dense and jargon-heavy with some run-on sentences, but nearly every clause conveys operative information rather than filler.

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?

No output schema and no annotations exist, so the description must cover the return contract, which it does (both the degradation dict and the job_result fields with units and expected ratios). The residual gap is that mesh-resolution parameters and the sif filename are never explained for a 15-parameter tool.

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% across 15 parameters, so the description must compensate and it partially does — flux_w_m2, t_in_c, k, t, cp, rho, velocity and length are tied to the energy-balance and solid-drop formulas, and case_dir is explained. But nx, ny_fluid, ny_solid, and sif receive no meaning in either the schema or the description, leaving several knobs undocumented.

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+resource ('Conjugate heat transfer via Elmer ... ONE solve spanning a plug-flow fluid channel AND a conducting solid wall coupled at their shared interface') and pins down the exact two-body configuration built. An agent can distinguish this from cht_graetz_submit or thermal_transient_submit without opening any schema.

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?

Gives clear operative context: requires ElmerSolver, degrades to a {ok:false, reason, install} dict rather than raising, accepts a prepared case_dir, and the applicability regime is bounded (cell Péclet ≈ 9, builder rejects > 25). It does not explicitly name an alternative sibling or state when to prefer cht_graetz_submit over this, so it stops short of 5.

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