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

Annotations already declare readOnlyHint and idempotentHint, but the description adds substantial behavioral context beyond that: staged rows are occurrences so collection-only fields like lithology are absent, classification is JSON and requires json_extract_string for rank rollups, and writes/file-reading functions are rejected. It also clarifies the relationship between search_occurrences and this staging step. This is rich disclosure beyond the annotations.

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 appropriately sized for a complex query tool and is front-loaded with the core purpose. Every sentence provides distinct value: use case, column hints, schema notes, prerequisites, and constraints. No filler or repetition of obvious 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?

For a tool with two parameters and an output schema, this description covers all decision-relevant context: what the staged data is, how to reference it, what can be analyzed, what fields are missing, how to handle JSON classification, and when to call describe first. An agent has everything needed to invoke this tool safely and correctly.

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 100% and both parameters are already described in the input schema, including the read-only SQL constraint and the source of the canvas_id. The description restates those details but adds little new parameter-specific semantics beyond reinforcing that table names come from search_occurrences. Baseline 3 is appropriate because schema already covers the parameters.

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 opens with a specific verb and resource: 'Run a read-only SQL SELECT against occurrence result sets staged on a DataCanvas by paleobiology_search_occurrences.' It clearly distinguishes itself from sibling search/describe tools by positioning itself as the analysis step after staging data. The purpose is unambiguous and agents can immediately tell it apart from the sibling 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 explicitly states when to use this tool: 'This is how you analyze a large fossil set without re-fetching it.' It also names the prerequisite alternative: 'call paleobiology_dataframe_describe first if you do not know the table or column names.' It sets clear boundaries with 'SELECT only; writes and file-reading functions are rejected,' which excludes misuse.

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