pulse_browser_fill

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: the value is ephemeral (never stored or returned), the form is never submitted, and an authorized_effects:["write"] grant is required. It also discloses the non-obvious side effect that focus is dropped by default and explains why, plus the exact set of field types that are refused.

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?

Four dense sentences, front-loaded with the action, then safety, then refusals, then the focus caveat. Nothing repeats the schema or the name, and the caveat about focus is placed exactly where an agent needs it before composing a multi-step call.

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 behavioral and safety picture is complete for a mutation tool with no annotations and no output schema, but the description never addresses how the target browser session is identified (app_id, port, target_url, expected_screen) — four of eight params left undefined in both schema and prose. An agent knows what will happen but not fully how to address the right context.

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 description coverage is 0% across 8 parameters, and the description only explains value, keep_focus, authorized_effects, and indirectly anchor_id ('mapped browser field'). The target-selection parameters — app_id, port, target_url, expected_screen — get no meaning at all, which matters for a tool that must act on the right browser session.

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 — 'Type a value into one mapped browser field' — which is unambiguous and clearly separable from pulse_browser_key (key presses) and pulse_browser_click (clicks). The scope word 'one' also tells the agent this is a single-field operation, not a bulk fill.

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 sequencing rule: 'Set keep_focus when a fill is followed by pulse_browser_key', naming the sibling and the condition that selects it. It also enumerates the field types that are refused, which tells the agent when this tool will not work. No general 'use X instead' routing for the other browser siblings, so it stops short of a 5.

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