notion_data_sources_query

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

The description frames the operation as 'Get the rows', i.e., a read, yet the annotations declare readOnlyHint=false, which tells the agent state can be mutated. That is a direct conflict about side effects. The extra context about filter nesting depth and the 400 on unknown columns is useful, but the contradiction in the safety profile dominates.

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?

Three tight sentences, all front-loaded: purpose first, grammar constraint second, prerequisite/pitfall last. No filler and every sentence contributes information an agent can act on.

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 complex nested-query tool the description covers the filter grammar and one failure mode, but says nothing about pagination (pageSize/startCursor are in the schema) or what the response looks like, and there is no output schema to fall back on. It is adequate but leaves meaningful operational gaps.

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%, so the schema already documents dataSourceId, body, and filterProperties fully. The description restates the filter-composition rule (one condition per type, and/or two levels deep) that the schema already documents, adding only the 400-on-unknown-column error behavior. Baseline 3 is appropriate when the schema carries the semantics.

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 gives a specific verb and resource: 'Get the rows of a data source', with the qualifier that results can be filtered and sorted. An agent immediately understands this is a read/query operation over tabular Notion data. It does not, however, name or contrast itself against sibling tools such as notion_search, so sibling differentiation is absent.

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?

Usage is largely implied by 'optionally filtered and sorted', and it adds a genuine prerequisite: 'Read the schema first if you do not know the column names'. It also warns that a filter referencing a non-existent column yields a 400, which steers the agent toward a correct call. What is missing is explicit when-not-to-use or an alternative tool to prefer.

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