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

The description adds useful behavioral details beyond annotations: it is 'unopinionated', returns parsed objects, and mentions cost. Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint; description reinforces these without contradiction.

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 front-loaded with the core purpose ('Raw metadata extractor') and lists what it returns in a structured way. It is concise but adequately detailed, with no wasted sentences.

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 output schema exists and the tool has only one parameter with good annotations, the description provides a complete overview of what metadata is returned, including grouping of meta tags and JSON-LD. Adequate for an agent to understand the tool's capabilities.

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?

There is only one parameter 'url' with 100% schema description coverage. The description mentions the URL pattern ('?url=') and cost, but the schema already sufficiently describes the parameter. Baseline of 3 is appropriate as description adds minimal extra semantic value.

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 it is a 'raw metadata extractor' listing specific elements (title, charset, lang, canonical, meta tags grouped by family, link relations, JSON-LD). It distinguishes itself from the sibling 'head-check audits' by noting that this tool just dumps the data without processing.

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 indicates the tool is for 'agents doing their own processing' and compares it to head-check audits, providing context for when to use this vs. an alternative. However, it does not explicitly state when not to use it or list other alternatives.

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