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

With no annotations provided, the description fully carries the transparency burden. It discloses the data source nature (deduped, tiered direct-feed), that it's a snapshot not live search, and the complete paid invocation flow (call without x_payment to get terms, sign, then call again). This goes beyond typical descriptions by explaining an unusual two-step payment mechanism.

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 dense but each sentence adds essential information. It is front-loaded with the primary purpose, then shifts to mode variations, then payment. While it is more than two sentences, every clause serves a purpose. Slightly run-on in spots, but overall efficient and well-structured.

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 tool has moderate complexity (5 params, payment flow, multiple modes) and no output schema. The description covers the main usage patterns, payment terms retrieval, and caveats. However, it does not specify the exact structure of returned headlines (e.g., fields like title, URL, date), which would be useful given there is no output schema. Still, it answers most practical invocation questions.

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%, providing a baseline of 3. The description adds meaningful context beyond the schema by explaining how parameters interact: q switches to archive search, category='ai'/'crypto' are curated cuts, and x_payment requires a specific handshake. This helps the agent understand the parameter interplay, justifying a score above baseline.

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 clearly states it provides 'Newest headlines from a deduped, tiered direct-feed pile' and explains the alternative archive search via q. It also distinguishes itself from a 'live web search,' clarifying its scope. This is a specific verb+resource with clear differentiation from potential siblings like read_url.

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 explicitly guides when to use each mode: 'Pass q to keyword-search the retained multi-day archive instead' and highlights special curated categories ('ai' or 'crypto'). It also details the payment workflow and points to the 'free `pricing` tool' as an alternative for price lists, offering clear when-to-use and when-not-to-use guidance.

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