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

Annotations carry only destructiveHint=true; the description adds genuinely useful behavior beyond them — the created status (not_started), the side effect of creating a job folder, the company-wide name uniqueness constraint, and the WRITE/POST endpoint. It omits what happens on a duplicate name (error vs. silent) and what the response contains. Note the destructiveHint=true on a pure create is an imprecise annotation rather than a description contradiction, since the description explicitly frames this as 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?

Four short sentences, front-loaded with what is created and its initial state, followed by the next-step pointer and the endpoint. The trailing 'WRITE.' is a compact mutability signal; nothing is bloated, though the endpoint notation is orientation-only.

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 create tool with no output schema, the description should tell the agent what comes back — most importantly whether the new job's id is returned so it can be fed to sortly_pull_items_into_job. It does not, and it is silent on duplicate-name failure behavior. The not_started status and folder side effect are well covered, but the return/next-step handoff is incomplete.

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 100% — every one of the 7 properties is documented inline with type, length and format constraints. The description only restates the uniqueness rule (already in the name field description) and adds no syntax or edge-case detail, so this is the baseline case where the schema does the heavy lifting.

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 ('Create a job') plus two distinguishing details: it also creates the job folder, and the job lands in not_started status. That is enough to separate it from sortly_create_item, sortly_create_alert and sortly_create_purchase_order 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 an explicit forward path ('Then use sortly_pull_items_into_job to record the stock it uses'), which is real routing guidance to a named sibling. It does not state when NOT to use this tool or whether a pre-existing job should be looked up first via sortly_get_job/sortly_list_jobs, so it stops short of full when/when-not coverage.

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