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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description usefully adds behavior beyond them: processing is asynchronous with summary/key points appearing 'in a few seconds' and read back via get_clip, and re-clipping the same URL updates rather than duplicates. What it does not clarify is what the destructive hint actually means in practice — e.g. that re-clipping overwrites existing note/title/workspace metadata on the prior clip — nor any auth or rate characteristics for the outbound fetch.

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?

Two tight paragraphs: purpose plus async/idempotency behavior first, then the anti-pattern routing. Front-loaded and free of filler. The parenthetical 'resumen y puntos clave aparecen en unos segundos, vía get_clip' is slightly dense but earns its place by telling the agent results are not returned inline.

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?

For a 5-parameter create tool with full schema coverage, annotations for the safety profile, and no output schema, the description covers what an agent needs: what it does, that results arrive later via get_clip, that repeat URLs update instead of duplicating, and where to route non-page text. Remaining gaps (exact destructive semantics) are secondary.

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%, so all five parameters (url, note, title, workspace_id, parent_document_id) are already documented in the schema, including the title fallback to the page title. The description adds no parameter-level guidance (e.g. how workspace_id resolution interacts with the URL identity used for de-duplication), 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 concrete verb and resource (save a web page as a clip) and immediately explains the mechanism: server fetches, cleans, and the AI summarizes, retrievable via get_clip. It also distinguishes itself from the near-miss siblings by name (create_document, Daily line), so an agent can choose without opening other schemas.

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 both a positive trigger (a URL that is a web page, same as pasting into the app) and an explicit negative trigger (text that isn't a page — notes, quotes) with the correct alternative tools named (create_document, diary line). Nothing is left to inference about when to pick this over siblings.

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