safari_read

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

With no annotations, the description carries the full burden. It discloses the read-only nature ('Read'), the specific data returned (URL, title, innerText, optional outerHTML), and the default tab selection. It does not mention error conditions or potential side effects, but 'Read' implies non-mutating, and the detail about what is returned is sufficient for an agent to understand the operation.

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 carrying distinct information: what is read, how to opt into HTML, and the default targeting. Front-loaded with the core purpose, no wasted words. Perfectly structured for quick consumption.

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?

The description covers the main purpose and the return content (URL, title, text, optional HTML). Since there is no output schema, it is the sole source of return info and does provide it. However, it omits the exact return format (e.g., JSON structure) and does not address error scenarios. It also does not distinguish from safari_js, which could also read content. Overall, it is fairly complete for a simple read operation, but not exhaustive.

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 coverage is 0%, so the description must explain all parameters. It explains include_html clearly ('Set include_html=True to also get the full outerHTML'), and it explains the default behavior for window/tab ('Omit window/tab to read the frontmost window's current tab'). However, it never clarifies what integer values for tab or window represent (e.g., indices, IDs) or whether both are needed together. This is a significant gap given zero schema documentation.

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 reads a Safari tab's URL, title, and visible text, and optionally the full outerHTML. This is a specific verb-resource pair that distinguishes it from siblings like safari_js (which executes scripts) and safari_click (which mutates). It unambiguously defines what data is returned.

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 only usage guidance is the default behavior when window/tab are omitted ('frontmost window's current tab'). It does not mention when to prefer this tool over alternatives like safari_js, nor any exclusions or prerequisites. No context about when NOT to use it is given.

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