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

Goes well beyond the annotations: discloses SMTP email sending, publishing into the analyzer's push module, the meaning of email_sent and push_queued (queued ≠ delivered), that a repeat call won't resend a confirmed email but may fill a missing push, and that it neither orders, charges, nor guarantees production. It even warns against claiming success when email_sent=false.

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?

Usage conditions are front-loaded, which helps, but the text is dense and repeats itself: 'Nie wymagaj ponownego przesyłania grafiki' and 'Grafika i parametry są już zapisane; nie przesyłaj ich ponownie' say the same thing, and the order_form/manual_review rules are interleaved with delivery semantics in one long run-on stream.

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?

Covers everything an agent needs before calling: prerequisite state from quote_patch, per-purpose preconditions, side effects (SMTP + push), result semantics, and idempotency behavior. The output schema exists and the description still explains the two status fields, so nothing relevant 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?

Schema coverage is 100%, so the baseline is 3; the description earns extra by adding cross-parameter rules the schema lacks — reuse only the quote_id and inquiry_token from that specific quote response, use haft for manual_review, and never derive email/consent from analysis_text or the image. It does not add much on email format or length limits, but those are already in 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?

States a specific action on a specific resource: it saves an inquiry ('Zapisuje zgłoszenie i powiadamia firmę') and routes it either to an order form or to a graphic-designer review. It also distinguishes itself from the quoting sibling by requiring quote_id/inquiry_token from quote_patch. It is clear, though the core purpose is buried under conditional instructions rather than stated up front.

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?

Explicit branching: purpose=manual_review with technology=haft only when the client supplied an email, consented to forwarding, and the project needs a graphic assessment; otherwise purpose=order_form. It also states hard exclusions — don't demand the graphic again, don't invent ChatGPT buttons, don't read the address or consent from analysis_text.

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