screen_connection_application

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

Beyond the annotations (readOnlyHint=false, idempotent, non-destructive), the description discloses genuinely useful behavior: a supervisory sanity gate, a possible requires_human_review outcome, a regulatory_override path, and a SHA-256 AuditReceipt. It also explains the token-saving default and points to the trajectory resource and plot.svg when raw arrays are omitted. It still does not say anything about runtime cost, solver failure behavior, or what the verdict tiers mean.

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 short paragraphs, front-loaded with the operation and then the default-output behavior, with no filler sentences. Density of unexplained jargon costs some readability, but nothing is wasted.

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 described, and annotations cover the safety profile. But for a 12-parameter, zero-coverage, end-to-end orchestration tool, the description leaves the majority of inputs and the tier/human-review decision logic unexplained, so an agent cannot confidently call it with meaningful arguments.

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 12 parameters, so the description must compensate and it does not — only include_trajectory is explained. Key domain parameters (force_tier2, asset_type, network_id, inverter_mode, operating_load_factor, feeder_background_scale, solver_timeout_sec) are left entirely to bare enum values and defaults, with no explanation of what force_tier2 or the fidelity tiers actually mean.

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 verb is "execute" and the object is "end-to-end progressive-fidelity triage" of a connection application, so the general domain is inferable, but the phrasing is a noun pile of internal jargon ("progressive-fidelity triage", "Supervisory Sanity Gate") rather than a plain statement of what is computed. It never explicitly says it orchestrates Tier-1 + Tier-2 screening, which is what would distinguish it from siblings run_tier1_screen and run_tier2_ac_study.

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?

There is no statement of when to use this versus run_tier1_screen, run_tier2_ac_study, classify_screening_regime, or sweep_connection_capacities — all of which overlap heavily in intent. The only usage-like guidance is about the include_trajectory default, which is a parameter preference, not tool selection. An agent must guess that "end-to-end" means this is the umbrella call.

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