last_heard

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

With no annotations provided, the description carries the full burden, and it does substantial work: it clarifies that 'actually play' means real playback rather than saved status, exposes the underlying walk mechanism, and discloses the page quota and early-termination behavior. It does not address the notable edge case of an artist not found within the walked window, nor explicitly confirm the operation is read-only.

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 compact sentences, with the core purpose and query intent front-loaded in the first sentence and cost disclosure in the second. Nearly every clause is load-bearing, but the parenthetical in the quota sentence ('max_pages, disclosed; stops early once all found') is slightly dense and could be parsed more cleanly.

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 moderate-complexity tool with 3 fully documented parameters and no output schema, the description covers purpose, mechanism, quota, and intended user question. Output shape is partially covered via '+ the gap' and the response_format enum in the schema. The main remaining gap is the not-found edge case and a precise description of the return payload, since no output schema exists to fill that in.

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 the schema already documents all three parameters and the baseline is 3. The description adds a small amount of meaning by tying max_pages to the disclosed quota ('stops early once all found'), but it adds nothing beyond the schema for artists or response_format. The added value is modest, not enough to push above baseline.

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 description uses a specific verb-plus-resource framing ('when did you last actually play them') and names the mechanism ('recently-played cursor walk') plus the computed output ('+ the gap'). It clearly answers the question 'when did I last listen to X?', which distinguishes its intent from raw-history siblings like get_recently_played. However, it never names a sibling explicitly, so differentiation is implied rather than stated.

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?

The description gives a concrete use case — answering 'when did I last listen to X?' for 1-10 artists 'without guessing' — which tells an agent when to select it. It also discloses quota behavior (🟡 2-10 pages, early stop), which helps with cost-aware tool selection. It does not state exclusions or name alternatives, so it stops short of a 5.

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