ai_search

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

With no annotations, the description carries the full burden. It discloses that it uses embeddings, ranks by semantic similarity, and returns up to 12 apps. This provides clear expectations about behavior and output, though it could mention if authentication is needed or if results are from a specific database.

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?

Two sentences: first states purpose, second gives usage hints and result details. Every sentence is information-dense with no filler. Perfectly concise and front-loaded.

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?

Given the simple single-parameter input and no output schema, the description covers all needed aspects: what it does, when to use, how it works (embeddings), and what is returned. No gaps present.

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% and the description mostly restates the schema's 'Natural-language description' with additional examples. Since the schema already explains the parameter well, the description adds only marginal value (e.g., examples), so baseline 3 is appropriate.

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 clearly states it is a semantic search for apps using embeddings. It provides examples of fuzzy intent queries, which distinguishes it from sibling tools like search_apps (presumably keyword-based). However, it does not explicitly name alternatives, making it a 4 rather than a 5.

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 explicitly says 'Best for fuzzy intent' and gives concrete examples, guiding when to use. It also mentions the result limit (up to 12 apps). However, it does not state when not to use or explicitly compare to siblings, so it lacks exclusions.

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