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

Annotations already declare destructiveHint, idempotentHint, and openWorldHint, so the description's job is to add context, which it does: it explains the public-contract boundary (bot deployments stay private), that paid listings force code protection, and that re-publishing updates and returns the existing listing. What it omits is the downstream consequence of publication — fees, takedown/reversibility, or whether stats become visible — though the privacy/protection disclosures are the highest-value ones here.

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?

Five short sentences, front-loaded with the core action and public/private boundary, then pricing and protection rules, then the sibling redirect. No filler or repeated phrasing; every sentence carries a distinct rule.

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 mutation with a nested tags object and no output schema, the description covers the decisions an agent cannot read from structured fields: what becomes public, how re-publish behaves, and the paid/protection coupling. Remaining gaps like backtestId reuse and currency defaults are already handled at 100% schema coverage, so completeness is good but not exhaustive.

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 100% schema description coverage, the schema already documents every parameter including tags enums and the paid-listing protection rule, so the baseline is 3. The description does add some framing around tags as categorization dimensions and the free-vs-paid model, but it largely restates what the schema already states, contributing little net new semantic detail.

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?

"Publishes a strategy to the public marketplace where users can discover it" gives a specific verb, resource, and audience/scope. It also distinguishes the public marketplace listing from private bot deployments, so an agent can tell it apart from strategy_share_link 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?

It states the primary use case (public discoverable listing) and names a concrete alternative with the selecting condition: "For private 1:1 sharing, use strategy_share_link(action=\"create\") instead." It also clarifies re-publish behavior rather than requiring a separate create/update decision. It does not address other marketplace siblings such as unpublish_from_marketplace or save_marketplace_publication, leaving that routing to inference.

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