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

Beyond the supplied annotations the description discloses latency (30–60 sec), the return shape (full text plus a link valid for 24 hours), the placeholder convention "[kitöltendő]", a privacy constraint (do not send personal identifying data), and a liability disclaimer ("Minta, nem jogi tanácsadás"). These are real operational facts an agent cannot infer from readOnlyHint/destructiveHint/idempotentHint alone.

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?

It leads with the resource and legal basis, then packs timing, output, disclaimer, and privacy guidance into short sentences with essentially no filler. The density of parentheticals in the first sentence slightly hurts scanning, but nothing is wasted.

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 generative tool with no output schema, the description covers document types, output form, retention of the link, and a data-handling restriction. The only gap is guidance on how the non-required parameters (amount, deadline, duration, consumer) shape the output, which the schema largely covers at 89%.

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 89%, so the schema already explains party_a, party_b, subject, amount, deadline, duration, and consumer. The description only restates this collectively as "a megadott felekkel és tartalommal" and adds no extra meaning (e.g. how `extra` or `consumer` influence the generated clauses), so the baseline 3 applies.

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?

A specific resource is named with its legal basis ("Szerződésminta a Ptk. szerint") and the six contract types are enumerated, directly matching the `type` enum. The enumeration also separates it from the sibling drafting tools `draft_privacy_policy` and `draft_terms`, which cover different document classes.

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?

The clause "A felhasználó kérésére hívd" gives a trigger condition and implies no proactive drafting, but it is close to a generic invocation rule. Nothing says when *not* to use it, and the near-neighbour siblings (draft_terms, draft_privacy_policy) are never named as alternatives.

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