Type

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

With no annotations, the description carries the full burden and does substantial work: it discloses that real key events are dispatched per character, that the resulting value is verified with mismatch reporting, that fast mode skips key events, and that date/time inputs bypass events entirely with isTrusted=false on the change event. It stops short of covering permissions, failure modes, or what a mismatch report looks like.

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?

A single dense paragraph that front-loads the core behavior and then attaches the flag semantics in order of likely importance. Every clause conveys information; the date/time aside is the only slightly tangential piece and it earns its place by flagging the isTrusted caveat.

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 an 11-parameter mutation tool with no annotations and no output schema, the description covers the action-defining flags and states that the value is verified afterward, which partially substitutes for a missing output schema. It omits the shared session parameters (slot, tab, agent, read, multiSlot), though those are documented in the schema and shared across siblings.

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 a baseline of 3 applies, but the description adds real meaning beyond the one-line schema entries for clear ('clears existing content'), submit ('presses Enter after'), and fast ('inserts very long text at once without key events'). The remaining parameters (slot, tab, agent, read, summary, multiSlot) get no description-level treatment, which caps this below 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?

States a specific verb and resource ('Types text into a ref element') and goes further by describing the mechanism (real key events per character). However, it never distinguishes itself from the sibling browser_fill, which likely also writes text into an element, leaving the agent to infer the difference.

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?

Usage is implied through flag semantics (fast=true for very long text, date/time inputs get direct value setting), but there is no explicit when-to-use guidance or any statement of when to prefer browser_fill, browser_press_key, or browser_select instead. The agent must infer selection criteria.

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