ui_read

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

Annotations already cover readOnly, non-destructive and openWorld. The description adds genuine constraints beyond them: it reads only *visible* elements and explicitly excludes credential fields, which is a meaningful safety boundary. It stops short of explaining failure behavior (no match, multiple matches, stale selector), which matters given idempotentHint=false.

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?

A single tightly packed sentence with the key constraints front-loaded ('one visible non-credential element') and the addressing method last. Nothing is wasted or padded.

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?

There is no output schema, yet the description never says what a read yields (text content, attribute value, existence flag), which is the main thing an agent needs to use the result. Annotations and schema are otherwise rich enough that the remaining gaps are moderate rather than severe.

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 100%, so the schema already documents all three parameters, including selector format and target_id/expected_layout_id semantics. The description only echoes 'exact selector' and does not add semantics for target_id or expected_layout_id, so baseline 3 applies.

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 one visible non-credential element') and narrows scope with 'by an exact selector'. This implicitly contrasts with ui_snapshot (bulk) and ui_find (search), but never names those siblings, so the differentiation is inferred rather than stated.

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 phrase 'by an exact selector' hints at when this is preferred over ui_find, and 'one' hints at preference over ui_snapshot, but there is no explicit when-to-use, when-not-to-use, or named alternative. Usage is only inferable from the description.

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