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

No annotations are supplied, so the description carries the full disclosure burden. It does reveal the analytical outputs and underlying physical models, which is meaningful context, but it never states that this is a pure/side-effect-free computation, whether results are advisory snapshots, or what the response looks like. For an unannotated tool this leaves real gaps.

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?

Two sentences with usage front-loaded, which is good structure. The second sentence is a packed list of seven jargon-heavy computed quantities that adds bulk without clarifying what any single output means or how it should be interpreted.

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 no output schema, the description's output enumeration (OCEI scores, lead time, battery mass, $/MTok) does double duty as a return-value sketch, which is useful. However, for a 7-parameter physical model with zero schema documentation, it omits return format, units, and parameter behavior, leaving the agent under-informed.

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 7 parameters, so the description must compensate and largely doesn't. There is loose implicit mapping (beta-angle eclipse ↔ beta_deg, Silicon Tj ↔ loop_temp_c, unit economics ↔ grid_price_usd_mwh, SEU ↔ storm_mode), but units, defaults, and the meaning of enum values like 'g0_quiet' versus 'live' are never explained.

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 ('Computes') and enumerates the resource: OCEI v2.2 scores, shockwave lead time, battery mass, radiator sizing, Tj throttling, SEU checkpointing, and $/MTok economics. An agent can tell this is an orbital-compute physics/economics evaluator rather than a scheduler. The dense in-house jargon (OCEI v2.2, Young-Daly, L1 shockwave) darkens the edges but the core purpose is legible.

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?

'Invoke before scheduling batch AI training/inference or evaluating orbital vs. terrestrial compute TCO' gives a clear triggering context. It stops short of exclusions or naming when to prefer compute_arbitrage_dispatch or solve_optimal_workload_allocation, so the boundary with siblings that also touch scheduling remains unstated.

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