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

Annotations already indicate readOnly, non-destructive, idempotent, and closed-world. The description adds substantial context beyond annotations: the distinction between requested and built capacity ('NEVER read a requested-MW total as installed or operating capacity'), the withdrawn-dominated nature of the full export, the presence of cited records with `source` and `as_of`, and the explicit non-inference of data-center load type. This enriches behavioral understanding without contradicting 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 description is exceptionally thorough but quite long. It is well-organized with a clear purpose statement, detailed field explanations, usage warnings, and sibling distinctions. However, some information could be condensed or presented in bullet points without losing value, and the repeated caution about requested capacity appears multiple times. Given the tool's complexity, this is still well-structured and front-loaded, but not maximally concise.

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?

Given the tool's high complexity and the minimal schema/annotations, the description is remarkably complete. It explains what records return (cited project-level data with full field list), how to group/filter, what caveats apply (requested vs built, withdrawn-dominated), and how to verify via `get_source_evidence_v1`. It also clearly delineates what is not included (data-center loads) and directs to alternative tools. The output schema exists, so return-value details are not duplicated, but the description covers all necessary usage context.

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?

The input schema is nearly empty (a single generic `params` object with no properties), so the description carries the entire burden. It explains that parameters are flat top-level keys, enumerates the filterable fields (state, county_fips, status, project_type, capacity_or_energy, fuel, project_ac_dc, transmission_owner, study statuses, submitted_date range, etc.), and provides concrete examples like `{"state": "VA", "project_type": "Generation Interconnection", "status": "Active"}`. This fully compensates for the zero schema coverage.

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 specific verb and resource: 'Query the PJM New Services (interconnection) queue'. It clearly distinguishes itself from sibling queue tools by explicitly naming PJM and referencing the other regional variants (MISO, CAISO, NYISO, etc.), leaving no ambiguity about scope.

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 explicit guidance on when to use this tool vs alternatives. It states 'For built/operating capacity use query_power_capacity_v1' and lists each regional queue tool for other ISOs. It also warns 'PJM only — never summed, deduped, or compared across ISOs', which directly specifies exclusions and conditions.

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