back

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

With no annotations, the description carries the full burden and does so well: it discloses the ownership gate (TAB_NOT_OWNED, TAB_INCOGNITO_NOT_SUPPORTED, TAB_OUT_OF_SCOPE), the concurrency cap and AGENT_CAP_REACHED payload, agent-scoped tab addressing, and that it is background-tab compatible and does not steal focus. It also enumerates status outcomes (ok, no_history, cross_origin, bf_cache, fragment_only) and typed error codes, which is exactly the kind of behavioral context an agent otherwise cannot infer.

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?

Front-loaded correctly, but the middle is bloated with duplicated content: cross-agent rejection/TAB_NOT_OWNED appears twice, and the typed error codes are enumerated once in prose (NO_BACK_HISTORY, CROSS_ORIGIN, BF_CACHE, FRAGMENT_ONLY) and again inside the status list. Tightening would remove roughly a third of the text without losing information.

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 no annotations and no output schema, the description is complete enough to invoke safely: it documents targeting scope, ownership rules, the return shape { status, resultingUrl, historyDepth }, the change_report payload, its truncation behavior, and the error codes. An agent has everything needed to call it and interpret the result.

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?

Only one parameter, and schema coverage is 100% (including the 'defaults to the agent's active tab' semantics), so the schema baseline is 3. The description adds genuine meaning on top: tab_id is agent-scoped and only tabs owned by the calling agent are addressable, with named rejection codes for incognito and cross-window tabs.

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?

Opens with a specific verb and resource plus scope: 'Navigate one step back in browser history on the agent's active tab,' and immediately constrains it ('Single-step only (no back(n))'). However, it never addresses the near-identical sibling `go_back` (nor `go_forward`), so an agent cannot fully disambiguate this tool from its own siblings from the description alone.

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 useful conditional context: targets the agent's active tab 'unless tab_id is supplied,' and recommends using change_report 'without calling read_page next.' But there is no explicit when-to-use/when-not guidance and no routing to the obvious alternative (`go_back`), which is the single most important selection question here.

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