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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description adds the sequencing contract with the mutation tools, which is real behavioral context. It does not say what the returned grammar looks like or whether it is workspace-scoped, and with no output schema that remains a small gap.

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?

Two short sentences: the first states the resource, the second the ordering constraint. The mandatory precondition is front-loaded with no wasted wording.

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?

This is a low-complexity, read-only, single-parameter tool, and the description covers its purpose and its required call order. Only the workspace_id semantics remain unexplained, which is minor for a tool whose main job is sequencing rather than filtering.

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?

The single parameter workspace_id has 0% schema description coverage and the description says nothing about it. It is not explained whether the grammar is workspace-specific, whether an invalid workspace id fails, or whether the skill is cached per workspace, so the description adds no meaning beyond the parameter name.

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: 'Returns the expression grammar for RudderStack Data Graph audiences.' It also names the sibling tools (create_audience, update_audience) whose expressions that grammar governs, so an agent can tell what this tool produces and where it fits.

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?

It states an explicit mandatory precondition: 'MUST be called before `create_audience` or `update_audience`.' That is a concrete rule for when to use this tool versus calling the audience mutation tools directly, so nothing is left to inference.

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