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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true. The description adds that the invoice is customized by PO number and company name, but 'generate' versus readOnlyHint leaves the agent unsure whether an artifact is persisted or merely returned, and no return format or external-service behavior is described.

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 front-loaded sentence with no filler that names the action and the two output artifacts. It is efficient, though it slightly blurs lookup and generation into one clause.

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?

With four parameters, no output schema, and openWorldHint=true, the description should say what comes back (document, URL, structured payload) and what the external interaction entails. It instead stops at naming the artifact, and leaves customer_email and output shape entirely undocumented.

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 25% (job_id alone is documented), so the description must compensate. It does clarify that po_number and company_name customize the invoice, but it says nothing about customer_email or about formats/defaults for any parameter, so half the parameters remain opaque.

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 specific verbs (look up, generate) and a specific resource (B2B Tax Invoice & Chain-of-Custody Certificate), so an agent knows this produces an invoice/custody artifact from a job. It does not differentiate itself from siblings such as calligraphy_get_job_status, which overlaps on the 'look up a job' half of the behavior.

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?

There is no explicit when-to-use or when-not guidance and no named alternative. The only contextual hint is indirect: the job_id parameter is 'returned by calligraphy_compile_board', implying the tool runs after compilation, but the description itself never states prerequisites or exclusions.

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