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

Annotations already establish readOnly/idempotent/non-destructive/openWorld, and the description adds substantial context beyond them: free with no sign-up, 100 lookups per day per caller, exactly one HTTPS GET of the home page, no result storage (only short-lived rate counters), and the fact that each observation is signed and dated as durable proof. It even discloses the delivery surfaces (Campus gateway via MCP, A2A, REST). That is unusually complete behavioral disclosure for a read-only 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?

The lead question is front-loaded and every core sentence carries information an agent needs (output shape, limits, cost, quota). It is dense but readable; the closing sentence about MCP registries and the Campus gateway is the weakest, only marginally useful for callers, and the block would scan faster with structure than as one long paragraph.

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?

There is no output schema, so the description must carry return semantics, and it does: a list of technologies with category, per-item confidence, and a signed dated observation. Combined with the quota, single-fetch scope and interpretive caveat, an agent has everything needed to call this correctly and to interpret results.

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?

With a single parameter and 100% schema description coverage, the schema already documents the bare-domain format and the no-scheme/path/port restriction; the description mostly restates it as 'one domain per call (no lists)'. It adds no new syntax, validation or format detail beyond the schema, so the baseline 3 applies.

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?

Opens with a specific verb-plus-resource question ('Which technologies does a site's public home page show?') and enumerates the exact categories returned, so an agent knows precisely what is being queried. It falls short of a 5 only because it never names a sibling (e.g. page_to_text, domain_health_check, page_search_ready) or states how it differs from those nearby page-inspection tools.

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?

Usage context is clear: send one bare domain, get back what the home page displayed, and it explicitly rules out lists, crawling and multi-page fetches. It also clarifies the epistemic boundary ('Statements are about what the page showed, not what runs behind it'), which prevents the agent from over-reading results. It gives no guidance on when to prefer this over comparable siblings, so 4 rather than 5.

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