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

Annotations already declare readOnly, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: the result set is capped at six, falls back to general designs when nothing matches, is numbered and carries the business name, and each result exposes a 'state' token that must be passed to the other tools. It does not describe ordering or why fewer than six may return.

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-loaded with the trigger condition, then the return shape, then the handoff to get_download, then the exclusions — a sensible order. Minor waste in the redundant 22-character note and slightly clunky phrasing ('with its name on them and numbered'), but every sentence broadly earns its place.

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?

There is no output schema, so the description must carry the return contract, and it does: six numbered designs, business name applied, state token per result, fallback behavior. Combined with annotations covering safety, nothing an agent needs in order to call this correctly 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 description coverage is 100%, so all four parameters are already documented, and the description's only added constraint ('names can be up to 22 characters') merely repeats the schema's business_name note. It adds no guidance on how colour or tagline influence matching, which is the one piece of semantic value the schema cannot carry.

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 ('find logo designs') and immediately bounds the scope: it produces up to six existing logo designs matched to what the business does, with the business name applied and numbered. An agent can distinguish it from get_download, update_design and start_build without opening any 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 triggering condition ('when someone wants a logo, business branding, a brand identity or a complete brand kit... and no Webba design has been chosen yet') and an explicit exclusion list (business names, non-logo imagery, editing an existing logo, trademark checks, general design advice). It also routes forward: once the person chooses, get_download is the next tool.

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