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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false. The description adds behavior the annotations do not cover: the operation is asynchronous (it queues a hosted job) and the result must be fetched via get_job, plus the filter is 'auditable'. That is genuine added value beyond 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?

Two sentences, no filler, with the core action front-loaded and the async follow-up second. Every sentence earns its place.

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 mutating, 7-parameter tool with a recursive nested expression and no output schema, the description covers the async result path well but omits the parameter semantics and revision/idempotency preconditions. It is adequate but leaves clear gaps an agent would need to close from the schema.

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 only 29% across 7 required parameters, so the description must compensate and it does not. It says nothing about expectedRevision, idempotencyKey, tableIds, projectId, or the nested definition/expression structure, leaving the agent to infer the most complex part of the call from the schema alone.

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 states a specific verb and resource: 'Create and assign an auditable project filter.' An agent knows this writes a filter into the project. It does not, however, differentiate itself from nearby siblings such as define_row_set, define_banner, or apply_transformation, so it stops short of a 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?

The second sentence gives a concrete workflow instruction: 'Queues a hosted job; use get_job to retrieve its result.' That tells the agent this is async and how to follow up, which is real guidance. But it says nothing about when to prefer this tool over define_row_set or apply_transformation, so usage is only implied.

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