storage_diff

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

With no annotations, the description carries the safety burden; it describes the comparison behavior and the diff output without ever stating explicitly that the operation is read-only or that it does not modify storage. It also does not disclose behavior when no matching earlier snapshot exists. The verb 'compare' suggests non-mutating behavior, but the description leaves side effects and error conditions unstated.

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 sentences with no filler; the first sentence front-loads the action, resource, and output categories, and the second adds a concrete use case. Every clause 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?

The tool is simple (one optional parameter, no output schema), and the description covers the main output categories and use case, but it leaves the parameter meaning implicit and omits error cases and explicit read-only behavior. It is adequate for a default-invocation call but not complete for custom snapshot names or failure handling.

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 only parameter, name, is undocumented in the schema (0% schema description coverage), and the description never explicitly maps name to the snapshot identifier. It only refers to 'an earlier storage_snapshot,' so an agent must infer that name selects that snapshot and has a default value of 'default'. This is insufficient compensation for the missing schema documentation.

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 action (compare) against a concrete resource (current storage vs an earlier storage_snapshot) and names the exact output categories: added, removed, or changed cookies/localStorage/sessionStorage keys. This distinguishes it from siblings like storage_snapshot, which would capture rather than diff, and from single-area tools like cookie_export or localstorage_get.

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?

Provides clear when-to-use context, notably the claim that it is the fastest way to find which key holds a session token. It implies a prerequisite (an earlier storage_snapshot must exist) but does not explicitly say to call storage_snapshot first or name alternatives that should not be used. Therefore it stops short of full when/when-not guidance.

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