Auto-Browser

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

With no annotations provided, the description carries the full burden. It adds critical behavioral context: 'All sensitive headers and bodies are automatically PII-scrubbed' (safety/privacy). It also implies the session must be capturing logs ('captured entries'), though it doesn't explicitly state activation requirements or whether reading the log clears it.

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?

Three sentences, each earning its place: (1) core purpose, (2) filtering capabilities, (3) privacy/safety behavior. No redundant words or tautology. Information is front-loaded with the primary action.

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 0% schema coverage and no output schema, the description should ideally sketch the return structure (what fields the entries contain). It identifies the resource type but not its shape. It also omits the limit parameter description. The PII-scrubbing note is valuable, but overall coverage gaps remain for a 4-parameter tool.

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%, requiring the description to compensate. It partially succeeds by explaining that method and url_contains are filters ('Filtered by method... or URL substring'), adding semantics beyond the bare parameter titles. However, it fails to explain the limit parameter's pagination role or session_id requirements, leaving 25% of parameters 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 clearly states the tool 'Return[s] captured HTTP request/response entries for a session' - specific verb (return), specific resource (HTTP request/response entries), and scope (session). This distinguishes it from siblings like browser.get_console (console logs) and browser.get_html (page content).

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 context by mentioning filtering capabilities (method/URL), suggesting when to use it (inspecting network traffic). However, it lacks explicit guidance versus close siblings like browser.get_request_failures (failed requests only) or browser.stop_trace, and doesn't state prerequisites like requiring an active capturing session.

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