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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile needs no restating. The description instead adds genuinely new behavior: a hard cap of 12 results, best-first ranking, and the shape of each result (creator, caption, still, page) – details absent from the annotation block. It stops short of explaining ranking semantics or whether a narrow query can yield zero results.

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 dense sentence pair with zero filler: searchable dimensions first, then the empty-query default, then the result contract. Every clause carries information an agent would otherwise have to infer.

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 no output schema, the description correctly shoulders the return contract – up to 12 works, best first, with creator, caption, still, and page – and all three parameters are covered by the schema. The main gap is the unresolved limit conflict (schema maximum 100 vs. "1 to 12") and the absence of any guidance on zero-result behavior for a read tool with a cap.

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 a 3 and the schema already documents all three parameters. The description earns extra credit by supplying natural-language query exemplars and framing the query as "what they show or are about," which meaningfully guides phrasing beyond the schema's "as a designer would type it." It does not, however, reconcile the schema's maximum of 100 with its own stated cap of 12.

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 (search) and resource (design works in Memorables) and enumerates exactly what can be searched – what a work shows, what it is about, creator/studio, and optional category filter. The quoted example queries ("ui animation", "logo with a dot") make the resource and matching behavior unambiguous, so an agent can distinguish this from get_work or similar_works 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?

It gives one clear usage rule – "With no query, the newest works" – so an agent knows the empty-query fallback. However, it never states when to prefer this over discovery siblings like similar_works or look_at_works, nor any exclusion or fallback path when few results are returned. Usage is implied rather than directed.

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