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

Goes well beyond annotations that only say readOnly=false, openWorld=true, idempotent=false, destructive=false: it discloses that no account is needed, that the draft expires in 7 days, that ownership requires opening a trial, and that the run takes about a minute. What it omits is what a repeat call does to an existing draft (regeneration vs. overwrite) and whether calls consume quota, which matters for a non-idempotent generative tool.

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?

Front-loads the verb and what gets built, then closes with the practical facts an agent needs (returned link, 7-day retention, no account, ~1 minute). Slightly promotional phrasing ('on Dar') and a long opening clause cost it a point, but nearly every sentence carries usable information.

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 still tells the agent what comes back (a viewable link) and how long it lives, which is the critical missing piece. Remaining gaps are secondary behaviors such as repeat-call semantics and what the draft looks like before the owner claims it.

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 name, city, kind, lang, from, phone, country, license, and about. The description only restates the core trio ('its name, city and services') and the 'in any language' hint for lang, adding essentially nothing beyond the structured fields. Baseline 3 applies when 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 ('Designs and writes the complete multi-page website of a real-estate office or property developer') and enumerates the output's scope (home with 3D hero, listings with search, services, about, contact with WhatsApp). This clearly separates it from the sibling real_estate_website_check, which audits rather than generates, and from property_listing_writer, which produces a single listing.

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?

Implies when to use it via the inputs it consumes ('from its name, city and services') and the 'No account' / trial framing, but never states when an agent should not call it or which sibling to prefer instead. There is no explicit alternative or exclusion, so an agent must infer routing from the distinctive output (a full site link).

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