Fetch a URL and return its current state: HTTP status, final URL after redirects, SHA-256 content hash, classification, readability score, title/meta-description, and wayback archive fallback if dead. Cached 10 minutes.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| max_bytes | No | ||
| timeout_ms | No | ||
| force_fresh | No | ||
| include_body_sample | No | If true, return first 1KB of body text. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
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 adds valuable details: caching for 10 minutes, wayback fallback for dead pages, and the inclusion of a content hash and readability score. It does not mention error behaviors, rate limits, or authentication, but the disclosures given are substantive and useful.
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 a single sentence that front-loads the core purpose and packs a detailed list of return components plus caching behavior without redundancy. Every element earns its place, making it highly efficient and easy to parse.
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?
Given the moderate complexity (5 parameters, no output schema), the description is surprisingly complete: it lists the output fields, notes caching, and mentions the wayback fallback. It lacks parameter guidance and edge-case details, but the provided information covers the main behaviors needed for an agent to invoke the tool reasonably. The lack of an output schema is mitigated by listing return components.
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 input schema has 5 parameters with only 20% description coverage (only include_body_sample has a description). The tool description does not explain any parameters, including max_bytes, timeout_ms, or force_fresh. Since schema coverage is low, the description should compensate but does not, leaving the agent to infer meaning from parameter names alone.
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 a specific action ('Fetch a URL') and enumerates the exact outputs returned (HTTP status, final URL, SHA-256 hash, classification, readability, title/meta, wayback fallback). This distinguishes it from siblings like linkpulse_classify, linkpulse_diff, and linkpulse_resolve by describing a comprehensive 'current state' check rather than a narrower operation.
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: use this when you need a comprehensive snapshot of a URL's current state. However, it does not explicitly state when to prefer linkpulse_check over siblings like linkpulse_classify or linkpulse_resolve, nor does it mention any exclusions or alternatives. The 'current state' wording gives some guidance but lacks direct contrast.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool serves a distinct operation: check fetches and analyzes a URL, classify works on already-fetched content, diff compares hashes over time, and resolve traces redirects only. The input and output contexts are clearly separated in descriptions, leaving little room for confusion.
All tools follow a uniform 'linkpulse_' prefix with a simple verb suffix: check, classify, diff, resolve. This consistent verb-only pattern makes the toolset predictable and easy to memorize.
Four tools cover the core needs of a link-checking utility without unnecessary bloat. Each tool adds a distinct capability—full inspection, offline classification, change detection, and redirect resolution—making the count well-scoped for the domain.
The tool set provides complete lifecycle coverage for the implied purpose: fetching and analyzing a link, resolving redirects, classifying content, and detecting changes. The wayback fallback in check also handles dead links, leaving no obvious dead ends or missing operations.