read_storage

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

With no annotations, the description must carry the full behavioral burden. It usefully discloses that the read is scoped to the active tab's origin and is non-mutating by implication, but says nothing about what is returned (key/value map vs list), ordering, or size/limit behavior when omitting both filters.

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?

One compact passage, front-loaded with the core action, then the parameter rules, with the cross-tool caveat in a trailing parenthetical. No sentence is redundant.

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 3-param read tool with no output schema and no annotations, the description covers scope, parameter interaction, and sibling disambiguation adequately. The main remaining gap is the shape of the returned data, which the agent would have to discover empirically.

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 0%, so the description has to compensate and does: it marks area as required, explains key as a single key, prefix as all keys beginning with a prefix, and specifies that omitting both returns everything — including the mutual-exclusivity rule the schema never states.

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 and resource ('Read keys from localStorage or sessionStorage') plus the scope ('of the active tab's origin'), which is information an agent cannot get from the schema. It also pre-empts the closest confusion by naming read_cookies as the wrong tool for cookies.

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 an explicit boundary against the sibling read_cookies and an in-tool rule for when to use key vs prefix vs neither. It does not say when reading storage is inappropriate versus list_storage_areas or read_indexeddb, but the routing it does offer is concrete.

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