browser_errors

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), but the description adds real behavior: the exact empty-result sentinel ('No errors captured.'), that it never touches the page, and the no-preview-open case. That is useful state disclosure beyond the structured fields, though return shape/pagination detail is absent.

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?

Front-loaded with the core scope and three tight sentences that each carry information. It loses a point for the awkward, opaque 'Reads what Reado captured' clause, which adds syllables without adding meaning.

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 a zero-parameter, read-only tool with no output schema, the description covers everything an agent needs: what subset is returned, the format, the empty case, and the no-preview case. Nothing material is missing.

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?

Zero parameters, so the baseline of 4 applies. The description correctly implies the tool takes no filtering input — scoping is baked in — and nothing about parameters is misstated.

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 ('Read only ... error-level console entries — errors and unhandled rejections — as JSON') and explicitly positions itself as 'the part of browser_console that answers "what broke?"', which distinguishes it from its closest sibling without opening either schema.

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 framing as a filtered subset of browser_console implies the selection rule: use this for error triage, use browser_console for the full log. No explicit 'when not to use' or named alternative is spelled out, so it stops short of 5.

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