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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds real value beyond them by disclosing that transform_code is a 'bounded JavaScript function', that the transform consumes exactly one result per ref, and that output is flat rows. That is genuine behavioral context not present in the structured fields.

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 sentences, front-loaded with the core action and its inputs, with no filler. The supported-chart-type list is long but earns its place by defining chart_spec's domain. Slightly list-heavy but structurally sound.

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?

With no output schema, the description carries the return burden and does address it ('returns flat rows'). For a 3-required-param tool with 0% schema coverage it covers the two most opaque parameters and the chart types. Minor gap: chart_spec's own keys and any size/rate limits on the bounded JS are unaddressed.

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 carry the parameter burden. It explains data_refs as 'an array of snapshot IDs' and transform_code as a 'bounded JavaScript function', and the chart-type enumeration effectively documents chart_spec's valid values. It does not describe chart_spec's internal structure, so it is not a full 5.

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?

States a specific verb+resource ('Create a chart') and enumerates exactly what it is built from (data_refs, a bounded JS function, chart_spec). An agent can distinguish it from dataframe-oriented siblings like run_metric_data or inspect_rows. It stops short of explicitly naming which sibling to use instead, so it does not reach the sibling-differentiating 5.

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?

'Query first and inspect rows' implies a prior workflow step, and 'the transform takes one result per ref' hints at the input contract. However it never names the concrete alternatives (e.g. inspect_rows, run_statement_data) or states when NOT to use this path, leaving routing to inference.

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