Paid tiered Browser-as-a-Service (/browse or /web-act). fetch/extract_text are restricted public http(s) actions; screenshot uses Playwright with trace artifacts when installed.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL to fetch | |
| tier | No | ||
| action | No | fetch | |
| wait_ms | No | ||
| agent_id | No | Optional caller agent ID | |
| max_bytes | No | ||
| viewport_width | No | ||
| viewport_height | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations mark this as read-only and open-world, and the description adds useful context: it is paid/tiered, fetch/extract_text are restricted, and screenshot uses Playwright with trace artifacts when installed. This goes beyond the annotations by disclosing cost, access restrictions, and implementation dependencies. However, it doesn't specify what happens on failure or rate limits, so not a 5.
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?
Two compact sentences convey the core purpose and key constraints. The first sentence is a fragment but still front-loads the tool's identity. Every phrase earns its place, making it efficient.
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?
With 8 parameters and 3 actions, this is a moderately complex tool, but the description is sparse. It omits return value formats, error handling, and parameter semantics, and the low schema coverage leaves gaps. The description is not enough for an agent to safely invoke the tool in all cases.
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 only 25%, with most parameters (tier, wait_ms, max_bytes, viewport dimensions) lacking descriptions. The description mentions the three action values and the paid tier, but does not explain the numeric parameters or their constraints. This leaves the agent with insufficient understanding of how to configure the tool correctly.
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 clearly identifies the tool as a Browser-as-a-Service with three distinct actions (fetch, extract_text, screenshot). It also mentions aliases (/browse or /web-act), making its purpose unmistakable. It distinguishes between the actions, which aids in selection.
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?
The description implies usage by stating it is a browser service, but does not explicitly say when to use it versus alternatives. It notes that fetch/extract_text are 'restricted public http(s) actions', hinting at constraints, but no sibling alternatives are named. The paid tier aspect suggests cost-consciousness but is not a complete usage guide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes, but there is potential confusion between 'decision' and 'reason', both offering advisory output. Also, 'review', 'witness', 'prove', and 'verify_proof' overlap in the proofs space, though descriptions differentiate them. Overall, an agent can disambiguate with careful reading.
All tool names use lowercase and underscores (snake_case), which is consistent. However, the verbs vary: some are imperative (e.g., 'browse', 'execute'), while others are nouns (e.g., 'signals', 'ledger'), breaking a strict verb_noun pattern. Overall, the naming is readable and mostly predictable.
With 30 tools, the surface is too large for a well-scoped server. Many functions could be separated (e.g., memory, workspace, feedback, marketplace). This excess makes it harder for an agent to navigate and select the right tool quickly.
The tool set covers core CRUD for memory and workspace, plus feedback, marketplace purchase, bounties, and verification. However, there is no tool to list or search marketplace listings, and workspace creation is only implicit via 'execute'. These gaps hinder fluid workflows.
