Get a page

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

The readOnlyHint annotation already signals safety, and the description adds genuinely useful behavior beyond it: truncation to fit the result budget, the semantics of each mode, and the windowing strategy for large pages. An agent knows what will happen when reading a big page.

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: action first, then addressing, then mode semantics, then content-specific reading strategies. Every sentence earns its place and none merely restates the schema.

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?

With no output schema, the description carries the burden of explaining return semantics, and it does: metadata, outline, content, and rendered are each described. Truncation is flagged, parameter combinations are clarified, and nothing essential for correctly invoking this read-only tool is missing.

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?

Although schema coverage is 100%, the description adds meaning beyond the schema: page_id OR path+locale are alternative addressing routes, mode changes what offset/max_chars/section mean, and section vs offset+max_chars are presented as explicit alternatives. This is exactly the relational context an agent needs.

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+resource: 'Reads one page', addressable by page_id or path plus locale. The four modes clearly define distinct output intents. It doesn't explicitly contrast with siblings like list_pages or get_page_version, but the 'one page' scope makes the purpose unmistakable.

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?

Gives clear within-tool guidance: choose 'outline' as the cheapest way to inspect a long page, use section or offset/max_chars for content, and warns that large pages are truncated. It does not, however, say when to prefer sibling tools such as get_page_version for historical content or list_pages for discovery.

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