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

While readOnlyHint and destructiveHint already indicate a safe read operation, the description still adds meaningful behavior beyond annotations: threshold_status vs production default, result_status=bounded_native_cap meaning the upstream faces at most 20 candidates and has_more is conservative, the absence of media URLs, and QUOTA per delivered row. This is valuable operational context for an agent.

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?

The description opens with the core behavior, then adds disambiguation, boundary behavior, output-usage guidance, and quota in a compact set of sentences. Each sentence carries information an agent needs; there is no filler or omitted critical nuance.

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 lightweight read-oriented tool with a strong schema, an output schema present, and helpful annotations, this description fills in exactly the gaps an agent cannot get from structured data: quota cost, upstream candidate cap, default threshold behavior, and which parameter to use. No critical external context 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?

The input schema already has 100% description coverage for the three params, so the baseline is 3. The description improves on that by explaining threshold semantics more concretely and by documenting that result cap is 20 and conservative, which directly makes limit and threshold more useful. It does not belabor the already-documented parameter types/defaults.

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?

The description states a specific action and resource: 'Find creatives that look the same as one creative' using a named mechanism, the production similarity index. It also adds an explicit disambiguation—'This is visual similarity, not exact creative membership'—which helps an agent distinguish this tool from exact-match or metadata-based search tools.

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 description clearly establishes the intended context: given one creative, retrieve visually similar creatives. It also gives follow-up guidance ('Returns metadata without media URLs; use get_media for selected ids') and clarifies semantics around threshold and result caps. It stops short of naming sibling tools like search_creatives or find_similar_ads for explicit when-not-to-use conditions, so it is not quite a 5.

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