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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds only that results carry page citations, which is a return-value detail already implied by the output schema; it says nothing about processing limits, how the different file inputs behave, or handling of scanned/non-text PDFs.

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 short sentence with no filler, though it leads with the output artefact rather than the verb. Nothing is wasted, but there is very little there to front-load.

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?

With six parameters, a nested file object, four mutually redundant file-location inputs and a large sibling set, the description should at least steer the agent on input selection and on summarization versus grounded Q&A. Annotations and the output schema cover safety and return shape, but the selection guidance gap is not covered anywhere the agent will look.

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 83%, so the schema already documents file_id, file_url, library_file_id, focus and the nested file object; the description adds nothing further. The real ambiguity is which of the four file-locating inputs to use, and the description does not address it. Baseline 3 applies when the schema does the heavy lifting.

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 sentence describes the shape of the output ('a plain summary and key points, each with the pages it comes from') rather than stating the action and resource directly; the name and title carry the verb. It gives no differentiation from near-neighbours like ask_pdf, extract_data or search_docs, which also consume a PDF and return derived content.

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?

There is no guidance on when to choose this over ask_pdf (targeted Q&A), extract_data (structured fields) or search_docs. No prerequisites, no mention of what kinds of documents suit a summary, and no exclusions.

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