diff_session_state

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

Annotations already declare readOnlyHint: true, so the safe read-only nature is known. The description adds value by naming the specific storage types compared, but it does not disclose the output format, how snapshots are structured, or error conditions. This is similar to the calibration example where the annotation covers safety and the description adds some context but lacks return/pagination details.

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 a single sentence that immediately conveys the core function. It is front-loaded with the verb and resource list, with no filler or repetition. Every word earns its place.

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?

Given the tool has two complex nested object parameters and no output schema, the description is too sparse. It does not explain the expected snapshot format, the structure of the diff result, or any potential edge cases. More guidance is needed for an agent to correctly invoke and interpret the tool.

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 no parameter descriptions (0% coverage), but the parameter names 'before' and 'after' are self-explanatory and the description reinforces their meaning. However, the nested object structure (what keys to include for cookies/localStorage/sessionStorage) is not explained, so the description only partially compensates for the schema's lack of details.

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 uses a specific verb 'Compare' and clearly identifies the resources (cookies, localStorage, sessionStorage) and the timing (before/after a page action). This fully distinguishes the tool from siblings like export_har_snapshot or record_page_flow, which have different purposes.

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 phrase 'before and after a page action' provides clear context for when to use this tool. It implies the workflow of capturing snapshots around an action, though it does not explicitly mention alternatives or exclusions. This is more than implied usage and provides a solid situational cue.

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