list_articles_page

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

No annotations are provided, so the description carries the burden. It discloses that metadata is upserted into a local SQLite store and bodies are not fetched. However, it does not mention permissions, error handling, or whether the operation is destructive beyond upsert.

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 short and front-loaded: two sentences with no fluff. Every sentence adds value, stating purpose, usage pattern, and a caveat about bodies.

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 tool with 3 params, no output schema, and mutation, the description covers the basic usage pattern and side effect (metadata storage). It lacks parameter details, return value description, and error handling. It is adequate but not exhaustive.

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 0%, and the description does not explain what fakeid represents or clarify begin and count beyond their names. The usage pattern implies begin increments by count, but no formal descriptions are given.

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 'Fetch one page of articles for a given fakeid and store metadata.' This is a specific verb+resource action, and distinguishes the tool from siblings like fetch_article (which fetches single article body) and crawl_incremental (incremental crawl).

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 provides explicit guidance: 'Use this for a first-time full crawl: call repeatedly with begin += count until the returned articles list is empty.' It also clarifies that bodies are not fetched here, helping the agent decide when to use this tool.

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