Create a project

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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world, so safety is covered. The description adds genuinely useful behavior the annotations don't: the project is analysed asynchronously in the background to recommend medias. However it says nothing about the required requestId de-duplication contract (which sits only in the schema), cost/credit implications, or auth/permission needs, which matter for a write.

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?

A single sentence that front-loads the selection trigger and then the effect; no filler, no restatement of the title.

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, 6-required mutation with no output schema, the description leaves out too much: the need to resolve topic/language/country via growwer_get_vocabulary, the requestId rule, and what the agent should do after creation (poll get_project?). Only the background-analysis outcome is conveyed.

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 only 67%, and the description adds zero parameter meaning — no mention of topics/language/country needing vocabulary lookups, no mention of the mandatory requestId, rootUrl format, or the 5–10 promotedProducts constraint. Required-but-undescribed parameters like rootUrl, name and websiteType are left entirely 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 sentence names a specific verb (creates) and resource (project) and adds the distinguishing precondition 'a website that has no project yet', which separates it from get_project/update_project and from create_order. Sibling tools are not named, which is the only thing keeping it from a 5.

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 gives an explicit trigger: use when the user wants to buy links and no project exists yet. That implicitly covers the when-not case (an existing project should route to create_order / get_project), but the alternative is never named, so the agent must infer it from the sibling list.

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