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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint=false, yet the description adds substantial non-obvious context: the 'pure-publisher posture' (no predictions or scoring), the ~4-day posting lag, the fact that documents themselves are not in the record, and that the primary file must be fetched via source_url. That is exactly the extra-behavior detail the annotations cannot supply.

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?

Three dense paragraphs but front-loaded with the return resource and trigger conditions before the docket-format reference material. Nearly every sentence carries operational value, though the record-shape inventory borders on schema duplication and could be tightened.

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 an 11-parameter, no-output-schema tool, the description compensates well: it describes the record shape (accession_number, category, class_types, libraries, authors/recipients), the join key (docket_number), and where the actual documents live. An agent has everything needed to query and interpret results.

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, but the description goes beyond the schema by decoding the docket-number grammar (prefix + year + sequence, with concrete examples per library), explaining that sub-dockets like 'RP26-930-000' resolve to the same proceeding, and clarifying the posted_date vs filed_date lag. The library concatenation quirk ('RulemakingElectric') is also surfaced as both schema and prose.

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?

States a specific verb and resource ('Returns FERC eLibrary document records'), enumerates the exact scope (Issuances vs Submittals across six libraries) and quantifies volume (~1,300 docs/week). This clearly separates it from adjacent siblings like get_federal_register_documents or get_enforcement_actions, which cover different sources.

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?

Gives explicit triggering conditions: 'Use this when the user asks about: a FERC docket or rate case, pipeline / utility / hydro regulatory activity, FERC orders affecting a company, or energy infrastructure proceedings.' No competing sibling is named for exclusion, but the tool's domain is narrow enough that this is clear context rather than an omission.

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