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

With no annotations, the description carries the full burden and delivers: exact payment address and cost, HTTP 402 failure mode, X-PAYMENT header requirement, JSON response after payment, chunk/pagination semantics, and a 304/recordCount 0 edge case (in the since parameter). For a paid endpoint this is exceptional disclosure of auth, cost, and failure behavior.

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 information-dense with no fluff, but it is a comma-spliced run-on that buries the lede: it opens with the URL and payment address rather than the tool's purpose. Chunk semantics, error codes, and identity clarifications are packed into one hard-to-parse paragraph, and 'Not a new SKU' adds cryptic ambiguity rather than clarity.

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?

The description thoroughly covers access mechanics — payment, pricing, pagination, auth, and the 402 failure mode. However, with no output schema and no annotations, it never describes what the returned JSON actually contains (fields of a FERC order, whether a chunk is a list or full text), which is a meaningful gap for a paid tool where an agent must judge whether the result satisfies the user's request.

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 100%, and the schema's own parameter descriptions are unusually rich — they already document pricing, chunk semantics, the page/since/before interaction, and the 304 edge case. The description adds framing around the overall pricing model but little per-parameter meaning beyond what the schema provides, so the baseline of 3 applies.

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 identifies a specific verb and resource ('FERC institution stipulation-and-consent text GET') and the agency domain 'FERC' implicitly distinguishes it from sibling tools like cfpb-orders, cftc-orders, and fdic-orders. However, the core purpose is never stated plainly — it is embedded mid-sentence between pricing details and the endpoint URL, so an agent must extract it.

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 gives clear parameter-level usage guidance: plain GET for the newest chunk, ?before for older chunks, ?since for newer-than-watermark, and ?id for one official text. It also explains the payment flow (unpaid returns 402, paid returns JSON). But it provides no tool-selection guidance against siblings like search, get-one, get-page, or ticks, and 'Not a new SKU' is cryptic rather than an explicit routing instruction.

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