get_assets_notes

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

With no annotations at all, the description carries the full burden and delivers thoroughly: it explicitly declares 'Read-only', explains the per-asset server query batching, discloses the cost profile (no tokens on assets without notes), and defines partial-failure semantics (failed array of {asset_id, error}; 'Success is true only when nothing failed'). This is rich behavioral context far beyond the bare schema.

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?

The purpose is front-loaded in the first sentence and the text is cleanly organized into Args and Returns sections. It runs a bit long (~150 words) and the Returns paragraph overlaps with the existing output schema, but given 0% parameter schema coverage and absent annotations, the length is largely justified.

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 batch read tool with variable-length input, partial-failure handling, and no annotations, the description is complete: purpose, use case, cost/safety behavior, parameter semantics, return shape, and a precise success criterion. Nothing an agent needs to invoke the tool or interpret its result is left to guesswork.

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 0% — asset_ids has only a title and array-of-string type. The description compensates fully by defining it as 'the candidates to check' with concrete examples ('an album's assets, a search result'), which tells an agent exactly what to pass and where that list comes from.

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, actionable purpose: it returns which of a batch of candidate assets already carry notes and their last verdict. The plural framing ('these assets', 'an album's assets') and the candidates-to-check semantics distinguish it from the singular sibling get_asset_notes, and no other sibling reads notes in batch, so an agent can select it confidently.

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 a concrete when-to-use scenario — a cleanup pass that wants to skip assets an earlier session already reviewed — and explains the cost rationale (the server is queried once per asset, no tokens spent on unannotated ones). It does not explicitly state when not to use it or name an alternative, so it stops one step short of full exclusion guidance.

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