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

Adds behavior beyond the annotations: the tool merges into existing content and never duplicates prior highlights ('Suma a lo que ya había: no repite los subrayados que ya estaban'), consistent with idempotentHint=true, and clarifies that the source is a browser page the agent already read under the user's session rather than a fresh fetch. It does not describe the response or what happens when a book already exists with conflicting metadata, so it stops short of full disclosure.

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?

Dense but front-loaded: the save action and its source come first, the sibling disambiguation second, the copy rules third, and the follow-up workflow last. Some clauses are packed into a single run-on sentence, but no sentence is filler.

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 single-parameter write tool with nested schema detail and no output schema, the description covers source, scope, dedup semantics, verbatim-copy rules, and the next steps the agent should take. The only unmentioned items (item limits, the missing/truncated fields) are already documented in the schema.

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?

The top-level 'books' parameter carries no schema description (0% coverage at that level), so the description must compensate, and it does: it tells the agent to copy each highlight literally, to include page or location when the page supplies them, and to include the user's note if one exists. It does not surface the schema's hard limits (max 20 books, max 500 highlights per book) or explain the 'missing' and 'truncated' fields, which remain schema-only.

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 ('Guarda en el cerebro del usuario los subrayados de Kindle'), adds the exact source ('read.amazon.com/notebook, con su sesión'), and explicitly names the sibling that is not this tool ('si el usuario tiene el archivo, usa import_highlights'). An agent can distinguish save_highlights from import_highlights without opening either schema.

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 an explicit alternative with its selecting condition (file available → import_highlights), a scope restriction ('Úsala solo con lo que el usuario ha subrayado'), and the downstream workflow ('después, sácales las notas con read_book y feed_brain (skill subrayados-kindle)'). Nothing about when to use it is left to inference.

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