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

With no annotations, the description fully carries the transparency burden. It discloses key behaviors: returns interactive/meaningful elements by default (or CSS selector), includes bounding box and visibility flag, explains locator field semantics (suggested, playwright, css, xpath), and describes pageId auto-pick logic. It also notes includeStyles adds computed styles. No destructive or permission-related information is needed for this read-only tool.

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?

The description is a single long paragraph but front-loads the main purpose and output. Every sentence contributes value—explaining output fields, locator recommendations, default behavior, and parameter details. It could be slightly more structured (e.g., bullet points for return fields) but remains efficient with no fluff.

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 no output schema, the description fully explains return values (tag, text, attributes, bounding box, visibility, locator fields). It covers edge cases (null suggested, auto-pick page, includeStyles toggle) and provides actionable guidance. The tool is well-scoped for its purpose, and the description leaves no critical gaps for an agent to use it correctly.

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 100%, but the description enriches several parameters: for pageId it explains 'Omit it to use the page ios_safari_navigate last landed on... only pass it to target a DIFFERENT tab'; for selector it clarifies default ('interactive/meaningful elements'); for includeStyles it specifies 'curated set of computed styles'. This adds significant meaning beyond the schema's basic type descriptions.

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 extracts 'locator-friendly element data from a Safari page for building Playwright/Selenium locators,' specifying the verb (extract), resource (Safari page elements), and output fields (tag, text, attributes, bounding box, visibility flag). It distinguishes itself from siblings like ios_safari_get_dom (full DOM) and ios_safari_evaluate (JS execution) by focusing on locator-ready data.

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?

Explicit guidance is provided on how to interpret results: 'USE suggested — the locator worth writing...', warning that 'css and xpath are diagnostic fallbacks, not recommendations' and that CSS path 'does not belong in a page object.' It also advises when suggested is null: 'act via ref and treat the missing test-id as the real finding.' This tells the agent exactly how to use the tool's output and when to rely on different locator strategies.

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