Peek — URL metadata & Markdown

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 explains that navigation, scripts, and styling are stripped, and that only public pages are supported. While it doesn't cover error handling or edge cases like redirects or dynamic content, the disclosed behavior is sufficient for the tool's simplicity.

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 concise sentences. The first states the core function and stripping behavior, and the second provides usage guidance. There is no redundant or irrelevant content.

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, the description adequately conveys purpose, input constraints, and output (Markdown). It doesn't mention potential errors or non-HTML content, but these are not essential for the described use case. The presence of a sibling tool doesn't introduce critical missing context.

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?

The schema already provides a thorough description of the url parameter ('Public http(s) URL of the page to convert') with 100% coverage. The tool description adds little beyond restating that the page must be public, so it does not significantly enhance parameter understanding 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 uses specific verbs ('Fetch', 'return') and a resource ('public web page'), and clearly states the outcome ('clear Markdown'). It also differentiates from the sibling tool by noting 'Use this to actually read a page,' implying peek_preview is for previewing rather than reading.

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 a clear when-to-use directive ('Use this to actually read a page') and indicates the input must be a public web page. However, it does not explicitly mention when not to use it or name the sibling tool as an alternative, so it stops short of a full 5.

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

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

No annotations are provided, so the description carries the burden. It implies a read-only operation via 'Get' and notes the page must be public, but it does not explicitly state side-effect-free behavior, error handling, or rate limits. The 'Fast and cheap' add performance context but transparency is incomplete.

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?

Two sentences, front-loaded with the action, outputs, and performance context. Every clause earns its place with no fluff or repetition.

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 read-only tool, the description covers the main outputs, use case, and performance. It lacks error behavior or limitations, but given the tool's simplicity and no output schema, the information provided is largely sufficient.

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% and the description adds no new meaning about the url parameter beyond what the schema already provides (public http(s) URL). The word 'public' in the description is redundant with the schema, so no semantic boost.

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 uses a specific verb ('Get') and resource ('link-preview metadata') and enumerates the exact output fields (title, description, OpenGraph image, etc.). It also distinguishes from sibling tool peek_markdown by saying 'not read it', clearly scoping the purpose.

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 states when to use ('when you need to describe or card a link') and when not to ('not read it'). However, it does not explicitly name the alternative tool, relying on sibling context rather than an explicit reference.

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