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

Annotations already mark the tool read-only and idempotent, and the description adds substantial behavioral context beyond that: the job completes in the background instead of failing, polling must continue until status 'done', retryAfterMs controls poll spacing, and the result is exactly what the original tool would return. No contradiction with annotations.

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 with no filler. The core action is front-loaded, the polling contract is stated compactly, and the key exclusion is at the end. 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 an async polling tool with one param and no output schema, this is complete: it defines the trigger, the polling loop, the stop condition, the wait interval, the result semantics, and the sibling tool to use instead for STEP jobs. An agent has everything needed to invoke this correctly.

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 100%, so baseline is 3. The description adds useful semantics by explaining that jobId is the handle received from a deferred call and that the same id should be used for polling. This goes beyond the schema's brief 'handle from a deferred call.'

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 and resource: 'Report on a job handle you were given.' It precisely identifies which deferred operations it applies to (evaluate, print_check, measure, check_interference) and explicitly distinguishes itself from export_step, so an agent can tell it apart from siblings without opening schemas.

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?

Gives explicit when-to-use guidance: after a slow analysis on a SAVED project returns a jobId, poll with this tool until status is 'done', waiting retryAfterMs. It also gives an explicit exclusion: 'STEP jobs are polled with export_step, not here.' This is clear and actionable.

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