context

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

No annotations are provided, so the description carries the behavioral burden. It does disclose deprecation status, the real-time behavior of the 'assist' mode, and the purpose of each mode. However, it does not mention side effects, permissions, data mutation, or error behavior, which is a notable gap for a tool with no annotation support.

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 well-organized with the deprecation warning front-loaded and modes broken into clear labeled sections. The mode/parameter layout is easy to scan. The only minor issue is the vague 'work with' phrase in the overview, which adds little information, but overall the structure is efficient.

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 tool has an output schema and the description covers modes, required parameters, and deprecation guidance, an agent can select and invoke each mode correctly. It lacks examples of context_data structure and a fuller explanation of what 'assist' returns, but for a deprecated compatibility tool with an output schema, the coverage is reasonably complete.

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%, so the description must compensate. It does by tying each parameter to a specific mode and marking required ones (e.g., conversion_id and context_data for store, sql_query or selected_text for assist). This adds meaning beyond the raw schema, although it does not describe the shape or expected format of context_data.

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 is deprecated and that it stores, retrieves, and works with SQL/PySpark conversion context, then enumerates three distinct modes (store, get, assist). Each mode has a concrete verb and resource, so an agent can generally tell what the tool does. The phrase 'work with' in the overview is vague, but the mode list resolves most ambiguity.

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 opens with 'Deprecated. Prefer convert. Still registered this minor version,' which is explicit routing guidance away from this tool to a sibling. It clearly tells the agent when not to use it, though it does not describe under what conditions, if any, this tool should still be chosen over convert.

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