query

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains FTS behavior (OR between words), how compound dishes are handled (not available as recipes), and includes a stop condition to avoid excessive searching. However, it does not explicitly state whether the tool is read-only or how errors are handled, but the read-only nature is strongly implied by the focus on SELECT queries.

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 is lengthy but well-structured with clear headings, emojis, and code blocks. Every section provides practical value—workflow steps, nutrient codes, schema documentation. While not minimal, the length is justified by the complexity of the domain; however, a few lines could be condensed without losing essential information.

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?

The description is comprehensive for a SQL query tool: it provides the database schema, key nutrient codes, example queries, and guidance on FTS behavior and compound dishes. With an output schema present, the description does not need to explain return values, but it still gives enough context to use the tool effectively without prior knowledge.

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 0%, with only the 'sql' parameter defined as a string. The description compensates by providing a complete schema, example queries, and nutrient codes, effectively explaining exactly what the sql parameter should contain and how to use it. This exceeds the baseline expectation for low schema coverage.

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 the tool's function: 'Execute SQL query on ANSES Ciqual French food composition database.' It specifies the resource (ANSES Ciqual database) and the action (execute SQL query). Even without siblings, the purpose is unambiguous and well-defined.

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 provides a detailed 2-step workflow with example queries, explicitly instructing users to first search, then retrieve nutrients, and to stop after finding a matching food. It also covers compound dishes and quick calorie lookups, giving clear usage context and guidance on how to structure queries efficiently.

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