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

Beyond the already-strong annotations (readOnlyHint, idempotentHint, destructiveHint=false), the description discloses substantial behavioral quirks: max_ttp_months is a HARD ISO-level cut with the consequence that <=30 can return nothing, max_fiber_km relies on a 'sparse ~260-node dataset over a county-centroid origin, NOT last-mile fiber,' ~83% geocoding coverage, and the default 'active' status semantics that account for SPP's non-standard labels. It also clarifies what baseload_only does NOT do (no peaker-vs-CCGT subdivision) and TTL/candidate-expiry semantics. No contradiction with annotations.

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 purpose is front-loaded in the first sentence, followed by filter semantics, then example, exclusions, and chaining — a logical ordering. It is long (~230 words) but dense: the tool has 9 parameters and several non-obvious behaviors, so the length is largely earned. Minor deductions for redundancy with the schema's max_ttp_months ISO table and the promotional tone of capitalized labels like 'ZERO-DRIFT CHAINING' and 'Phase 2 LIVE.'

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 9-parameter, high-complexity tool with an output schema, this description is remarkably complete: it covers scope and stats, the return shape (site_evaluation_handoff, by_iso/by_fuel summary), edge-case warnings (empty results under 30 months), exclusions, a worked example, and downstream chaining (candidate_id → analyze_site/rank_sites). The only unresolvable detail — the default limit value — is explicitly punted in the schema itself ('default varies by tool'), so the description is not at fault.

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 100%, so the baseline is 3 — and indeed the schema independently documents every parameter, including the ISO-level TTP table. The description adds value above baseline by tying parameters together: the worked example showing how min_mw, fuel_type, and max_ttp_months compose, the note that iso combines with max_ttp_months 'as an intersection,' and that max_fiber_km implies geocoded rows. This is a step above baseline but not a full 5 since much parameter detail is duplicated in the schema.

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 opens with a precise verb-resource-scope statement: 'Server-side SET-REDUCTION over the US ISO interconnection queue' returning 'ONLY the survivors.' It then explicitly differentiates from siblings by naming what this tool is NOT — the ISO-level GW aggregate (get_interconnection_queue) and single-site reads (analyze_site) — so an agent can disambiguate without opening sibling schemas.

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?

Provides an explicit when-to-use rule ('Use for high-cardinality siting/arbitrage scans') and an explicit do-NOT-use rule with named alternatives ('do NOT use for the ISO-level GW aggregate (use get_interconnection_queue) or a single-site read (use analyze_site)'). It also includes a copy-pastable worked example call (min_mw=1000 fuel_type=gas max_ttp_months=34) and chaining guidance for analyze_site, leaving nothing to inference.

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