browser.select

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false), it discloses scope (collection), effect (gui), operation completion, no undo, the long-running wait/timeout behavior, and an explicit enumerated error set including staleSession. The clarification that stale sessions cause failure is exactly the kind of behavioral context annotations cannot carry.

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 key constraint (replaces selection, browser must already be open, exactly one selector) is front-loaded in the first two sentences, followed by compact metadata and an error list. The metadata line on scope/effect/undo is boilerplate but each token carries actionable 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?

For a GUI-mutating, long-running operation with no output schema, the description covers preconditions, selector exclusivity, async behavior, undoability, and the failure surface. An agent has everything needed to decide whether to call it and how to interpret a failure.

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 100%, so the baseline would be 3, but the description adds meaning the schema cannot: card IDs resolve to their cards in card mode and note IDs to their notes in note mode, and it reiterates the either/or constraint. It does not further explain session or timeout tradeoffs beyond the schema text, so it falls short of a 5.

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 names a specific verb and resource ("Replace selection in an already open browser") and immediately differentiates itself from browser_open by stating it "does not open a closed browser." It also spells out the mutually exclusive selector semantics, so an agent can distinguish this from siblings like browser_getSelection.

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?

It states the precondition (an already open browser), the exclusivity rule ("Exactly one selector"), and the mode-dependent meaning of cardIds vs noteIds, which is real guidance about when a given call is valid. It stops short of explicitly routing the agent to browser_open for the closed-browser case or naming browser_getSelection as the read counterpart, so a 4 rather than a 5.

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