search_page

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

Since no annotations are provided, the description must carry the behavioral burden. It usefully discloses that it operates on 'visible text' only and returns 'surrounding context,' and implies a cheap read operation. However, it doesn't specify how frames are handled, what happens with zero matches, or explicitly confirm it has no side effects.

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 sentences, front-loaded with the core behavior and followed by a concise cost/usage tip. Every word earns its place; no fluff or redundancy.

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 no output schema, no annotations, and 5 parameters (only 1 documented in schema), the description provides too little. It leaves the return object structure, frame scope, and regex/case semantics unexplored, so an agent would need to infer or experiment to use it with confidence.

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 only 20%, with just 'text' described in the schema. The description only hints at 'surrounding context' (corresponding to context_chars); it doesn't clarify regex, case_sensitive, or max_matches behavior. Although parameter names are reasonably self-explanatory, the description fails to compensate for the 80% of undocumented parameters.

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 specific verb and resource: 'Grep the CURRENT page's visible text' and the output 'return matches with surrounding context.' It differentiates from snapshots/screenshots by scoping and cost, but doesn't explicitly contrast with sibling search tools like 'search' or 'find_by_text', so it stops short of full sibling differentiation.

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?

It gives an explicit recommendation to use it first to locate terms because it 'costs nothing compared to a snapshot or a screenshot.' This is useful when-to-use guidance, but it doesn't mention when not to use it or compare it to other text-finding siblings, leaving some alternatives unexplored.

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