describe_page

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

With no annotations, the description carries the full burden and does disclose the essential behavior: it returns a compact summary plus an enumerated `intent` classification. It does not explicitly state that the page is not modified, but the read-only nature is strongly implied by 'describe' and 'summary'.

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 compact and front-loaded with the core value proposition. The intent enum is useful and earns its place, and the comparative cost note is one short clause. No filler exists.

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 zero-parameter read-only utility, the description explains what the tool returns, the key fields covered, the intent taxonomy, and how it fits into agent workflows. There is no output schema, so this fills the needed gap without requiring further documentation.

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 tool has zero parameters and schema coverage is 100%, so there is nothing for the description to add about arguments. The baseline of 4 applies because parameter semantics are simply not a concern for this tool.

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 opens with a specific outcome: 'Compact LLM-friendly page summary (title, heading, key buttons, forms)' and then identifies a unique differentiator, the classified `intent` field. This clearly distinguishes the tool from browser_snapshot and other snapshot-like siblings.

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?

It explicitly positions the tool against browser_snapshot ('Cheaper than browser_snapshot for agent context') and explains when it is valuable ('agent can branch with one read'). It does not spell out exclusions or say when a full snapshot is necessary, so it falls just short of fully explicit when-not guidance.

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