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

No annotations are provided, so the description carries the full behavioral burden. It does disclose one useful behavior (empty query returns all records), but is silent on read-only safety, result ordering, pagination, and what a returned recipe looks like.

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?

Compact and front-loaded: the definition of a recipe comes first, followed by illustrative examples and the empty-query edge case. Every sentence earns its place, with only mild redundancy against the schema on the empty-query point.

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 two-parameter search tool with no output schema and no annotations, the description supplies enough to select and invoke it correctly. The main gap is that returned recipe contents are not characterized, which a sibling like get_recipe may cover.

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 both limit and query are already documented in the schema. The description's restatement that query is natural language and empty means all records adds nothing beyond the schema, so baseline 3 applies.

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 (recipes), and defines what a 'recipe' is (a procedure combining multiple MCPs to complete one task) with concrete query examples. This separates it from the bare resource name, though it never names get_recipe or search_mcp as the adjacent alternatives.

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 examples ('fix a high-churn product page', 'automate weekly reports') imply when this tool fits, and the empty-query behavior is given. However, it never states when to use get_recipe instead of searching, nor any exclusions, so routing between siblings is left to inference.

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