browser_logs

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

No annotations exist, so the description carries the full burden and does substantive work: it discloses that reads succeed on blank/unresponsive pages, that capture requires a supported page, that credential headers and named secrets are redacted, and that eviction is surfaced via data_loss. It never explicitly states the call is side-effect-free or describes rate/size limits beyond the schema's bounds.

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 tight sentences, front-loaded with what the tool reads and its key robustness property. The main cost is over-compression: 'Capture changes require a supported page' is too terse to be actionable without defining 'supported page'.

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 an 8-parameter tool with a nested object, no annotations, and no output schema, the description covers pagination and data-loss signaling but omits what the response contains (how next_seq and data_loss are returned) and leaves several filter parameters unexplained. It is adequate rather than complete.

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?

With schema description coverage at only 38%, the description must compensate, and it partially does by explaining after_seq continuation semantics and capture's page-support prerequisite. But level, limit, max_chars, url_contains (already in schema), and tab_handle get no added meaning, and the interaction between limit and max_chars/eviction is unstated.

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?

Names a specific verb (Read) and a precise resource (buffered console, network or navigation events) with an explicit temporal scope (since claim). It is clearly distinct from mutation siblings like browser_click or browser_navigate, though it doesn't name an alternative read tool such as browser_read_text or browser_snapshot to sharpen the line.

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?

'Even if the page is blank or unresponsive' gives a useful condition for when this tool still works, and the after_seq/restart-at-0 sentence tells the agent how to continue vs. re-filter. However, there is no guidance on when NOT to use it or which sibling (browser_read_text, browser_snapshot, browser_evaluate) to prefer for other read needs.

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