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

Goes well beyond the readOnlyHint/openWorldHint/destructiveHint annotations: it discloses cost (~$0.00001, charged per call), the spending cap semantics (budgetUsd default 2, max 10) and that chargedUsd reports actual cost, plus a non-obvious auth requirement ('Needs the write scope'). The write-scope note does not contradict readOnlyHint — it is an auth quirk, not a mutation claim — and is exactly the kind of context an agent cannot infer.

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-loads the core capability in the first clause, then batches the practical constraints (follow-up tool, cost, budget, auth) into short trailing sentences. Dense but every sentence carries information an agent needs before calling.

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 9-parameter, enum-heavy search tool with an output schema already covering return shape, the description supplies the missing pieces: when to use intent vs sort, cost and budget behavior, the follow-up read step, and the auth scope. Nothing required to invoke it correctly is absent.

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 a baseline of 3 applies, but the description adds real meaning on top: it explains what 'intent' represents (topic and angle, semantically matched) and how budgetUsd/chargedUsd interact as cap and receipt. The remaining parameters (sort, platform, mediaType, sourceKind, minJudgment, makeableOnly) are left entirely to the already-thorough 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 ('Search our judged library of real posts and videos that already performed') and describes exactly what comes back (ranked shortlist with numbers, hook, format). It also distinguishes itself from the natural follow-up sibling, reference_read, so an agent can separate the search and read steps without opening either 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?

Gives clear usage context: supply an intent (topic and angle) to get exemplars, or omit it and rank by 'sort' for the top of the shelf, with the destination for follow-up explicitly named ('Read the ones you want with reference_read'). It does not explicitly rule out the near-neighbours references_browse/references_list/references_suggest, so the exclusion side is only implied.

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