Compare actual browser-session token usage against estimated screenshot costs to track perception overhead and choose lower-cost browsing actions.
Tokens que ha devuelto agentic-browser en esta sesión frente a lo que habrían costado las capturas de pantalla (una por cada percepción, ancho×alto/750).
| Name | Required | Description | Default |
|---|---|---|---|
| reset | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full behavioral burden. It discloses that the comparison is session-scoped and gives the screenshot-cost formula, but it says nothing about whether the optional 'reset' mutates state, whether the tool is read-only, or what the response contains. That leaves a meaningful behavioral gap for a tool with a reset parameter.
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 description is a single dense sentence with no filler, and the comparison being reported is front-loaded. The parenthetical formula earns its place by explaining how screenshot cost is estimated, though the sentence could be clearer with an explicit action verb.
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 that there are no annotations, no output schema, and an undocumented reset parameter, the description is too thin. It explains the metric but omits reset behavior, return shape, and usage context, which are all needed for correct invocation.
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%, and the description never mentions the single parameter 'reset'. It therefore adds no meaning beyond the bare schema and fails to compensate for the low coverage, leaving reset semantics entirely undocumented.
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 specifies what is being reported: tokens returned by agentic-browser this session versus the cost of equivalent screenshots, including the width×height/750 formula. That is a fairly specific resource, though it never states an explicit verb like 'returns' or 'reports' and leaves the reader to infer that this is a stats tool. Sibling tools contain no other stats tool, so differentiation is adequate once the purpose is inferred.
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 gives no indication of when to use this tool versus alternatives, no preconditions, and no mention of when not to use it. It also does not explain what the 'reset' option is for, so an agent has no guidance on whether or when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.