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

Annotations already declare idempotency and non-destructiveness, and the description confirms 'Idempotent across retries' plus adds value the annotations cannot: the explicit non-effects (no copy, no follow, no publish) and the read-access requirement on the source list. It does not say what the save appears as on failure or whether duplicate saves are silently no-ops beyond the retry claim.

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?

Three short sentences, front-loaded with the action and destination, then the id source, then the side-effect exclusions. No 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 no-output-schema, two-parameter write with full annotation coverage, the description covers destination, source access, id provenance, and non-effects. Minor gap: it doesn't say where the saved pick surfaces afterwards (saved_items/my_library) so an agent can verify or chain.

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 coverage is 100%, so both parameters are already documented in the schema, and the description largely restates the id source. It adds the 'yours or anyone's' clarification of sourceListId scope, but no syntax or format detail beyond the 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 verb and resource ('Save one pick'), the destination ('Library under Saved picks'), and the source scope ('a list you can read, yours or anyone's'). The negations ('Does not copy the pick, follow or publish') distinguish it from siblings like save_list or follow_curator without requiring the 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?

Establishes the precondition (the list must be readable, own or others') and points to get_list_items/list_items as the id source, which is real usage context. It stops short of explicitly naming when to prefer it over the near-duplicate sibling add_saved_item, leaving one ambiguity.

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