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

With no annotations provided, the description carries the full behavioral burden. It does disclose useful traits: server-side fetching, the pricing model (free tier, then $0.001/call via x402), and conditional fields ('when present'). However, it omits rate limits, redirect-following behavior, auth requirements, and error semantics for a network-fetch tool — material gaps when annotations offer zero coverage. The pricing disclosure and server-side note earn it above a 2, but the missing fetch-behavior details cap it at 3.

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 information-dense sentences with no filler. The mandatory action is front-loaded ('Fetch a URL server-side'), followed by a compact enumeration of return fields and then the endpoint/pricing note. The field list is long but earns its place as it substitutes for the absent output schema. Only minor trimming of the endpoint reference (already implied by the tool name) would tighten it.

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 one-parameter tool with no output schema and no annotations, the description does reasonable work: it lists the returned fields, which partially compensates for the missing output schema, and it discloses pricing. But it lacks rate limits, error handling, redirect behavior, and authentication notes, all of which matter for a server-side network fetch. Complete enough for a basic call, yet with clear gaps an agent would benefit from.

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% for the single url parameter, which the schema already describes as 'Absolute http(s) URL to fetch.' This puts the baseline at 3. The description adds marginal value by explaining that the fetch is server-side and by listing what metadata the returned fields will contain, but it does not specify URL constraints beyond what the schema's uri format already conveys. Adequate but not compensating 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 gives a specific verb ('Fetch') and resource ('a URL server-side') and enumerates the exact structured outputs (title, description, canonical URL, OpenGraph/Twitter fields, favicon, language, timestamps). It is clearly distinct from siblings: read_url presumably returns raw content, while this returns parsed metadata, and it names the underlying endpoint (GET /v1/meta). An agent could select it correctly without opening the schema.

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 'Same free tier as read_url' phrase acknowledges a pricing relationship with a sibling but does not explicitly state when to choose get_metadata over read_url (e.g., 'when you need parsed metadata rather than raw HTML'). No exclusions, prerequisites, or alternative-routing conditions are given beyond an implied cost/pricing context. The guidance is present but left to inference.

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