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

Annotations declare idempotentHint=true and readOnlyHint=false, and the description usefully adds that the call is asynchronous (queues a hosted job) with results fetched via get_job — behavior not derivable from the structured fields. It does not state permissions or failure modes, but it materially improves the agent's mental model.

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, zero filler, with the async behavior front-loaded. Every clause 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 six-parameter, non-idempotent-looking job-queuing tool with no output schema and low parameter coverage, the description is thin — it explains the async handoff but omits wave compatibility requirements, what the job compares, and how to interpret results.

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 coverage is only 33% and the description adds nothing about the six required parameters. Concepts like fromWaveId/toWaveId are only obliquely implied by 'across project waves', and tableId/projectId are unexplained; the description fails to compensate for the coverage gap.

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 (compare) and resource (tables across project waves) with a qualifier ('compatible') that constrains scope. It does not name or differentiate against any sibling, but the purpose is unambiguous.

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 implies async workflow by saying it queues a hosted job and points to get_job for the result, which is real operational guidance. However, it gives no criteria for when to use this vs. siblings like run_table or render_project_table, nor any prerequisite (e.g. waves must be compatible).

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