A/B test reels with trial reels

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

Substantially exceeds the annotations: it discloses that each version consumes the publishing limit, that trial reels are shown to non-followers first, that a background service evaluates after decide_after_hours, and that a winning version may be auto-republished. It also states a hard platform limitation (Meta's API cannot graduate trial reels) and the confirmation_token prerequisite, which are exactly the behavioral facts an agent needs before calling a write tool.

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 purpose, then layered with behavior, lifecycle, and constraints in a logical order. Every sentence carries information, though the trailing fragment "Asks the user first" is tersely attached rather than integrated.

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 an 11-parameter publishing tool with no output schema, the description covers the preconditions, side effects, post-publish lifecycle, and the result (winner or "inconclusive"). Minor gaps remain around staggered publishing and what the immediate call returns, but nothing critical to a correct invocation is missing.

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?

With 64% schema coverage, the description fills key gaps: it gives the decide_after_hours default and range (48, 12-168), explains the practical consequence of share_winner "republish", and clarifies what a variant represents (hook, cut, caption, cover). It does not touch stagger_minutes, template, publish_at, hypothesis, or account, leaving those 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?

The first sentence names a specific verb and resource (publishes reel variants as trial reels) and constrains the count (2-4 versions). It is distinguishable from the sibling publish_reel, publish_trial_reel, and get_ab_test without opening any 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?

It explains the situation the tool is for (testing hook/cut/caption/cover differences without spamming followers) and constrains the setup ("Versions should differ in one thing"). It also flags the approval gate ("Asks the user first"). It stops short of naming an explicit alternative such as publish_trial_reel for a single trial or list_ab_tests for monitoring.

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