Search suggestions

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the trailing 'Read-only.' is redundant. What the description does add beyond annotations is substantive: the return shape ('JSON with total and a suggestions array of strings') and the fact that narrowing is conditional (country only narrows city/state, make only narrows model). No gaps that would cause misuse.

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?

Front-loaded with purpose and the reason to use it, then Args and Returns in a scannable block; no filler sentences. Minor waste: the 'Read-only.' clause restates annotations and the Returns line restates an existing output schema.

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 5-parameter, one-required lookup tool, everything an agent needs is present: legal enum values (absent from the schema), filter interactions, intended call ordering relative to search_metadata, and response shape. Nothing required to invoke it correctly is left to inference.

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 0% and there are no enums in the schema, so the description carries the full burden — and it does. It enumerates all six legal values for suggestion_type and explains each optional filter's narrowing relationship, which the bare string schema with empty defaults does not convey at all.

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+resource ('Distinct values present in the library for one field') and ties it to its consumer: 'the exact spellings search_metadata expects'. That linkage to the sibling search_metadata makes the tool's role unmistakable against search_cities/search_places, which return assets rather than vocabularies.

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?

Explicitly prescribes when to call it ('Use this before filtering by city or camera to avoid guessing') and motivates it with a concrete failure example ('iPhone 14 Pro' vs 'iPhone14,3'). The dependency chain from this tool to search_metadata filtering is spelled out rather than implied.

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