snapshot

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

With no annotations, the description carries the full burden, and it does disclose one real trait: the default return is a diff rather than a full dump. However, it is cryptic about what is being diffed, when, and against what baseline, and it omits format, size, and safety context entirely.

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 short sentences, front-loaded around the core purpose, with no filler. The brevity is clean structurally, though it comes at the cost of the clarity issues above.

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 page-capture tool with no annotations and no output schema, the description should explain what a snapshot contains and how it differs from a screenshot or page report. It leaves the agent guessing about return format, diff semantics, and the nonexistent full-map option.

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 schema has zero parameters and full coverage, which would normally be a baseline 4. But "unless you ask for a full map" implies an optional mode parameter that the empty schema does not provide, actively misleading the agent about how to request the full-map behavior it advertises.

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?

"What is on the page now" conveys that this captures current page state, but the verb is implicit and it does not distinguish itself from siblings like screenshot, page_report, or read_text, which also surface page content. An agent cannot tell from this text what kind of snapshot (DOM, text, image) is returned.

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 only usage cue is "unless you ask for a full map," which gestures at a mode but names no condition, prerequisite, or sibling alternative. There is no explicit when-to-use guidance against the many other page-reading tools in the sibling list.

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