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

With no annotations, the description carries full disclosure burden. It usefully states 'Read-only' and reveals that it performs URL probes, but says nothing about network behavior, timeouts, auth requirements, or what happens when no alternative is found — significant gaps for a network-fetching tool.

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?

A single front-loaded sentence that names the action, the alternative it replaces, and the concrete artifacts probed, with zero padding.

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?

The enumeration of discovered endpoints is the most useful part, but with no output schema and no annotations the description should clarify the return shape (e.g., list of URLs, single result, or failure mode) and whether requests require permissions. It is adequate for a one-parameter tool but leaves real gaps.

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?

Only one parameter (url) exists and the schema provides 0% description coverage. The description implies the URL is the target site but adds no format, validity, or scope detail (e.g., base URL vs full path) beyond the obvious.

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?

States a specific verb ('Find') and resource ('machine-friendly way into a site'), then enumerates exactly which discovery artifacts it probes (llms.txt, /.well-known/mcp.json, agents.json, openapi.json, ai-plugin.json, MCP URLs). This scope definition clearly separates it from check_agent_access and check_many, which imply verification rather than discovery.

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 clause 'instead of scraping its HTML' implies the usage context — reach for this before falling back to HTML scraping — but there is no explicit when-to-use/ when-not guidance and no sibling is named as the alternative. Adequate but leaves routing to inference.

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