query_power_capacity_market_pjm_v1Query cited PJM Base Residual Auction UCAP clearing prices, RTO cleared MW, reliability requirement, and published administrative price collar by delivery year and LDA.
| Name | Required | Description | Default |
|---|---|---|---|
| params | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds the 'cited' qualifier, indicating results include evidence references, and 'internal' in the title, but it does not disclose additional behavioral traits such as pagination, rate limits, or response size. The added context is useful but minimal.
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 a single, focused sentence with the verb front-loaded. Every phrase adds value, and it avoids repetition of the tool's name or title. It is compact yet information-dense.
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 has an output schema (not shown) and simple input requirements, the description provides the core domain context: what data fields are available and by which filters. It does not explain how to construct parameters or handle edge cases, but for an internal query tool with minimal expected complexity, it is largely sufficient.
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 essentially empty (anyOf object/null with additionalProperties true), providing zero parameter names or types. The description compensates by stating the logical filtering dimensions 'by delivery year and LDA', which informs the agent what inputs matter. It does not specify exact parameter names or formats, but the guidance is meaningful for a 0% coverage 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 the specific verb 'Query' and clearly identifies the resource as 'PJM Base Residual Auction' results, listing exact data points (UCAP clearing prices, RTO cleared MW, reliability requirement, administrative price collar) and dimensions (delivery year, LDA). This distinguishes it from sibling query tools that target other PJM or power-market metrics.
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?
The description clearly implies the tool is for obtaining cited PJM RPM auction results, which gives clear context for when to use it. However, it does not explicitly mention alternatives (e.g., 'use describe_power_capacity_market_pjm_v1 for metadata') or exclusions, so it stops short of full guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each capability has a clearly named describe/query pair, and domains like power, AI infrastructure, robotics, and space are distinct. The generic describe_capability_v1/query_capability_v1 could be confused with the named variants, and the many ISO-specific interconnection queues share similar names, but descriptions explicitly disambiguate them.
All tools follow a consistent lowercase snake_case verb_noun pattern: describe_<capability>_v1 and query_<capability>_v1, with a few utility tools like list_capabilities_v1 and get_source_evidence_v1. There is no mixing of conventions.
At 62 tools, the set is far too large for typical server scope. The describe/query pairs inflate the count even though each is justified, and the generic capabilities plus per-ISO variants make it feel heavy and hard to navigate.
The server covers each domain thoroughly with describe, query, and evidence verification, plus generic fallbacks for capabilities not yet in the client's tool list. Minor gaps exist (e.g., no county/state attribution for some data, no load types in ISO queues) but they are explicitly documented and workable.