feed_archive

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

With no annotations provided, the description carries the full behavioral burden and does so admirably: it discloses that the endpoint is public and credential-free, paginated with a fixed pageSize, limited to a 30-day window, excludes whale-movement items, and returns a specific response envelope. This goes well beyond what annotations would typically provide.

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 but verbose and somewhat redundant: 'paginated 30-day history' and 'covering the last 30 days' restate the same idea, and 'public, MCP-compatible' plus 'without any credentials' are repeated. It is structured with em-dash separators but would benefit from trimming duplicate phrases.

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?

Despite having no output schema, the description explains the full response shape and item fields, all four optional parameters, pagination behavior, and excluded data — everything an agent needs to call the tool correctly. The only flaw is that the description is cut off mid-sentence at the end, but the provided content is otherwise complete.

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. The description adds extra semantics beyond the schema: it clarifies the default type is 'all non-whale-move items', notes pageSize is fixed at 20, explains the q filter's case-insensitive matching on title and summary, and gives an example. These details genuinely help an agent construct valid calls.

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 states a specific verb ('Returns a paginated archive') and resource ('crypto news articles, analysis, and AI-generated summaries from the CryptoWhaleInsights feed'), and explicitly differentiates from siblings by calling out that whale movement events are excluded and pointing to the whale-movements endpoint. An agent can immediately tell this is the news/analysis feed tool, not a whale-tracking or market-data tool.

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?

It explicitly says AI agents can use this to read news/analysis without credentials, and gives a clear when-not case: whale movement data is excluded, use /api/public/whale-movements instead. It also documents fixed pageSize, defaults, and filter behavior, leaving little ambiguity about when to invoke this tool over alternatives.

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