search_saved_audiobooks

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

No annotations exist, so the description carries the full burden, and it delivers meaningfully: it discloses the underlying endpoint ('GET /me/audiobooks paged'), the client-side filtering mechanism (results are filtered locally from paged data, not server-side searched), and a quota indicator. It does not disclose what happens at the scan_cap boundary (truncation) or auth requirements, but the disclosed mechanism and quota context are genuinely useful.

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 short sentences with zero filler: purpose and mechanism first, then quota cost. Every word earns its place, and the structure is appropriately sized for a simple search tool.

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?

Adequate for a 4-param, 0-required tool with no output schema: the schema documents most parameters and the description conveys scope, mechanism, and quota. The gaps are the lack of sibling routing (search_audiobooks vs this tool) and no statement of what happens when scan_cap is reached — does the user get partial results, a warning, or an error?

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 75% — query, max_results, and response_format are documented in the schema, but scan_cap is not, and the description adds no parameter-level semantics. The phrase 'bounded walk' hints at scan_cap's role as the bound but never says so explicitly, which is a gap since scan_cap is the most behaviorally significant parameter.

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 states a specific verb+resource ('Search saved audiobooks') and adds the mechanism ('bounded walk + client-side filter'), which is clear and distinctive. The 'saved' scope differentiates it from sibling search_audiobooks, though it stops short of explicitly naming which sibling to use instead.

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?

Usage context is only implied: 'saved audiobooks' indicates a user-library scope, and 'bounded walk + client-side filter' implies a local scan with cost bounds. There is no explicit when-to-use vs when-not-to-use guidance, and with siblings like search_audiobooks (all audiobooks) and get_saved_audiobooks (plain paged listing) the agent must infer the routing on its own.

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