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

The description discloses several behavioral details beyond the readOnlyHint annotation: 'Title matches rank first' indicates result ordering, 'description is cut to about 300 characters here' explains truncation, and 'organization is an exact publisher name' plus 'jurisdiction is the source's own word' specify the expected matching semantics. No contradictions with the annotation are present.

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 concise, consisting of four short sentences, each adding distinct value. It avoids unnecessary verbosity and presents information in a clear, readable manner without requiring a formal structured format.

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 9 parameters and no output schema, the description is incomplete for practical usage. It does not explain return values, pagination, or the meaning of several parameters, nor does it provide enough context to understand how to effectively query datasets. The two explanations provided are helpful but insufficient for a complex search tool.

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?

While the schema has no parameter descriptions, the tool's description explains the semantics of two parameters (organization and jurisdiction) and hints at the query parameter via 'by words in the title, keywords, or description.' Other parameters (as_of, limit, cursor, fields, format, snapshot_id) remain undefined, leaving significant gaps.

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 purpose: 'Find open.canada.ca datasets by words in the title, keywords, or description.' It is unambiguous and differentiates from sibling tools by focusing on text-based search across specific fields.

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 implicit usage guidance by referencing sibling tools: 'get_dataset returns it whole' suggests using that tool when full descriptions are needed, and 'organization is an exact publisher name from list_organizations' indicates that list_organizations should be queried for valid values. However, it does not explicitly state when to choose this tool over others.

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