nyt_article

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose that the tool returns 'metadata and body paragraphs' and that it works with 'public' articles, which implies paywalled content may not be accessible. However, it doesn't disclose potential rate limits, whether the tool handles redirects, what happens with invalid URLs, or whether the returned content is truncated. The 'public' qualifier is useful but the description could be more transparent about failure modes.

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 two sentences and front-loads the core action ('Get a New York Times article's content') before adding detail about return type and input. Every sentence earns its place. It could be slightly more structured by separating the return value description from the input requirement, but it's appropriately sized for a simple one-parameter 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 simple one-parameter tool with no output schema, the description covers the essential information: what it does, what it returns, and what input it needs. However, it doesn't mention whether the returned metadata includes author, publication date, or other fields, and it doesn't clarify behavior for non-public or paywalled articles beyond the 'public' qualifier. Given the tool's simplicity, this is adequate but not 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 description coverage is 100% – the single parameter 'url' is described as 'Canonical NYT article URL' in the schema. The description adds the qualifier 'canonical article URL' which reinforces the schema but doesn't add significant new meaning. The description's mention of 'canonical article URL' does clarify that non-canonical or shortened URLs may not work, which is a small addition beyond the schema.

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 the tool's function: 'Get a New York Times article's content' and specifies it returns 'metadata and body paragraphs from a canonical article URL.' This is a specific verb+resource combination that distinguishes it from sibling tools like nyt_headlines or nyt_categories. However, it doesn't explicitly differentiate from other article-fetching tools like nydailynews_article or nzherald_article, though the NYT branding makes the resource clear.

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 implies usage context by specifying 'from a canonical article URL' and noting it returns 'one public' article, which suggests it's for fetching individual articles rather than lists or searches. However, it doesn't explicitly state when to use this tool versus alternatives like nyt_headlines, nyt_categories, or nyt_author, nor does it mention any exclusions or prerequisites beyond the URL requirement.

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