page_watch

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

With no annotations, the description carries the full burden and does add useful behavioral context: data is stored locally, it captures accessibility labels and state, explicitly never form values, and the site allowlist still applies. It omits error/overwrite behavior and what a compare actually returns.

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?

Three tightly-packed sentences, front-loaded with the core purpose, followed by the action breakdown and constraints. No filler.

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 4-param tool with no annotations and no output schema, the description is adequate but leaves gaps: the parameter for 'delete' is unspecified, tabId handling is unmentioned, and the comparison result (which the absent output schema would normally cover) is never sketched.

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 only 25% (only tabId documented), so the description must compensate, and it does partially by mapping which action uses name vs watchId — information the schema does not convey. However, it never mentions tabId and omits which parameter 'delete' requires.

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 pair ('Save a local page checkpoint and compare it later') and enumerates the modes (create/compare/list/delete). It distinguishes itself from lookalike siblings such as snapshot and read_as_markdown by emphasizing the later-comparison workflow.

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 action-to-parameter mapping (create→name, compare→watchId) gives implied usage per mode, but there is no explicit guidance on when to prefer page_watch over snapshot/get_html, nor any prerequisites or exclusions.

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