read_tab

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

Discloses the key behavior that refs are renumbered after actions, making earlier reads stale. No annotations provided, so the description carries the full burden; it adequately covers the read-only nature and output variations, though it does not detail error cases or performance.

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?

Front-loaded with the core purpose, followed by essential guidance in a well-structured Args list. Every sentence is necessary and no fluff. Extremely concise for the information conveyed.

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 the tool's complexity (multiple modes, staleness concern), the description covers why to read before actions, what each mode returns, and the source of tab_id. An output schema is available, so the brief return statement suffices.

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?

Adds significant meaning beyond the bare schema: tab_id is 'The handle returned by open_tab,' and mode explains all three options ('snippet', 'urls', 'structure') with their purposes. Schema coverage is 0%, so the description compensates effectively, though it could note that mode has a default.

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 it reads the current state of an open tab, using specific verbs and resource identification. It distinguishes itself from sibling tools by emphasizing that element refs ([eN]) come from the latest snapshot and are renumbered after actions.

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?

Provides explicit guidance to read_tab right before an action because refs become stale, and explains the three modes ('snippet', 'urls', 'structure') with their intended use cases. This differentiates from alternative tools like fetch_snippet or fetch_urls.

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