Get Refined Queue

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

Annotations cover read-only/idempotent safety, and the description adds substantial behavior beyond that: the HARD ISO-cut semantics of max_ttp_months (SPP ~24 is the only ISO under 30, so <=30 can return nothing), the ~83% geocode rate, the sparse ~260-node fiber dataset with county-centroid origin ('NOT last-mile fiber'), and the 7-day-TTL candidate/snapshot contract with 'deterministic candidate_expired on lapse — never a silent recompute.' None of this contradicts the readOnly/idempotent 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 purpose, method, and scale are front-loaded in the first sentence, with the example and the critical hard-cut NOTE well placed immediately after the parameter list. The tail (CANDIDATE CONTRACT, ZERO-DRIFT CHAINING — roughly a third of the ~280 words) is verbose for a tool description and some of it could be condensed to 'see contract doc,' though nearly every sentence does carry a real behavioral fact.

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, 0-required tool with spatial predicates and cross-tool chaining, the description covers purpose, example, return shape (backed by an output schema), data-quality limitations, exclusion conditions, and the chaining contract — nothing needed to invoke it correctly is missing. The only minor gap is explicit truncation/pagination behavior when survivors exceed the limit parameter.

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% with rich per-field docs, so the baseline is 3; the description earns a 4 by adding combinatorial guidance the schema lacks — the worked call (min_mw=1000 fuel_type=gas max_ttp_months=34), the 'use >=34' threshold to avoid empty results, and the cross-parameter guarantee that geocoded_only=true carries both the handoff and frozen coordinates.

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 opening sentence names a specific mechanism and resource — 'Server-side SET-REDUCTION over the US ISO interconnection queue' — with scale context (~5,300 projects, 7 ISOs, ~1,744 GW). Two concrete example queries ('show me 1 GW+ gas projects that can connect in under three years') and the explicit 'do NOT use for the ISO-level GW aggregate (use get_interconnection_queue)' clearly disambiguate it from the most confusable siblings.

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?

Contains an explicit routing rule: 'Use for high-cardinality siting/arbitrage scans; do NOT use for the ISO-level GW aggregate (use get_interconnection_queue) or a single-site read (use analyze_site).' It also instructs chaining survivors into analyze_site via site_evaluation_handoff and candidate_id, so the agent knows both what this tool is for and what comes next.

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