list_embedded_files

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

readOnlyHint=true already covers the safety profile, and the description adds real value beyond it: it explains the viewer/wrapper pitfall and the intended two-step save workflow. It does not mention ordering, error cases, or empty results, which keeps it from a 5.

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 definition, then the practical caveat, then the arg note. Minor redundancy in the closing sentence ('Open the URL this returns, then save that tab instead'), but every sentence carries information.

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?

No output schema, so the description correctly specifies what is returned (URLs of the underlying files) and what to do with them. For a single-param read-only tool this is complete, with only error/empty-result behavior left unspecified.

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 0%, so the description must carry the parameter explanation, and it does: 'Tab number, window.tab, or text from its title or URL.' That is meaningful disambiguation of accepted input forms beyond the bare string schema.

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 resource and output: URLs of files embedded in a page, qualified as PDF viewers/iframes and 'the real file behind a viewer.' An agent can distinguish this from list_page_links by the embedded-file framing, though the sibling is never named explicitly.

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?

Gives concrete context and a follow-up workflow: LEARN wraps PDFs in a viewer, so saving the tab saves the wrapper; instead open the returned URL and save that tab. It states when and what to do next, but does not contrast against alternatives like list_page_links or read_pdf.

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