fsi_pressure_plate_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 thoroughly: async/off-channel execution, subprocess-only heavy solvers, LGPL-3.0 dependency, and an explicit degradation path ({ok:false, reason, install, stack} when the stack is absent). It also discloses the immediate return shape and the polling contract, which is exactly what an agent needs to handle this long-running job.

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?

Dense but mostly front-loaded: the solve and its stack come first, then degradation behavior, then physics knobs and return contract. Every sentence carries technical content, though the phrasing is heavy enough to be slightly hard to parse on first read.

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 complex asynchronous multi-physics job with no output schema and no annotations, the description covers execution mode, failure mode, return values, and the polling target (job_result giving time_windows, tip_disp_m, coupling_converged, case_dir). Nothing essential for correct invocation is missing.

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 coverage is 0%, so the description must compensate and largely does, naming 9 of 10 parameters and grouping them semantically (fluid: inlet_velocity_m_s/nu_m2_s/rho_kg_m3; solid: youngs_pa/poisson/density_kg_m3; coupling: end_time_s/time_window_s/max_iterations). It omits the `timeout` parameter and gives no units or ranges beyond the names, so it falls short of full compensation.

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 (partitioned FSI solve on the preCICE OpenFOAM↔CalculiX stack) and explicitly differentiates itself from siblings by naming the analytic oracles it is the 'real coupled-field twin' of. An agent can separate it from fsi_plate_deflection and fsi_interface_balance 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?

Clearly positions usage against alternatives: it is the real coupled twin vs the analytic oracles, runs asynchronously OFF the MCP channel, and instructs the caller to poll job_result afterward. It stops short of an explicit 'use this when X, use the oracle when Y' rule, so it is strong context but not full routing guidance.

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