Search posts that performed

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

Annotations already declare readOnly/openWorld/destructive hints, and the description adds genuinely non-obvious operational facts: per-call cost (~$0.00001 from credit), that budgetUsd caps spend (default 2, max 10), that chargedUsd reports the actual cost, and that the call requires the write scope despite being a read. These are things the annotations and schema do not convey.

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 the core verb+resource, then cost/scope constraints, with no filler sentences. Slight redundancy in restating budget defaults ($0.00001 cost, budgetUsd default 2 / max 10) that the schema already declares, which keeps it from a 5.

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, zero-required tool with an output schema and read-only annotations, the description covers the two risk areas an agent actually needs — cost/budget and required auth scope — and defers ranking/output details to the schema. It does not explain how the optional intent and sort interact when both are supplied, a minor gap.

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 already 100%, so the baseline is 3, but the description adds real meaning: intent is defined as 'topic and angle' and flagged as semantic (related exemplars match without shared words), and budgetUsd is framed as a spend cap whose result surfaces via chargedUsd. Remaining params (sort, platform, mediaType, minJudgment) are left to the 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?

Specific verb (search) plus a precisely scoped resource: 'our judged library of real posts and videos that already performed.' It also states the output shape (ranked shortlist with numbers, hook and format) and names the follow-up sibling reference_read, so an agent can separate it from reference_read, concept_search and news_search without opening a 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 ('give the intent and get a ranked shortlist') and explicitly routes the next step to reference_read for retrieving full items. However it never states when to prefer this over neighbouring discovery tools such as concept_search or find_evidence, so the alternative set is only partially covered.

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