IETF

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

Annotations only include readOnlyHint=true, so the description carries the burden of behavioral disclosure. It adds valuable context: the tool supports multiple actions, RFCs have native DOIs, and inspected RFCs are 'automatically tracked on the research shelf.' No contradictions with 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 well-structured with headers like 'Actions:' and 'Query formats:', and it front-loads the core purpose. While it is fairly long, each section serves a function and avoids fluff. Slight redundancy with schema descriptions but acceptable for a multi-action tool.

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 complex tool with 6 parameters and 4 actions but no output schema, the description explains the purpose of each action and provides query format examples. It also notes integration with web_fetch_incisive and the research shelf. It doesn't describe return structures, but the lack of an output schema makes this a minor gap.

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%, with detailed descriptions for every parameter (action, query, status, wg, limit, offset). The tool description's 'Query formats' section essentially paraphrases the schema, adding little new parameter-level meaning beyond what the schema already provides.

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: 'Search and retrieve IETF RFCs, Internet-Drafts, and standards-track documents.' It then enumerates distinct actions (rfc, search, draft, subseries), clearly distinguishing this tool from siblings like arxiv or web_fetch_sections.

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 states 'Use this for RFC lookups' and lists concrete use cases. It also notes that 'RFC Editor and Datatracker URLs are also handled automatically by web_fetch_incisive,' which provides an alternative tool for URL input. However, it doesn't fully elaborate when to prefer other siblings like arxiv or kagi_search.

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