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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds real behavioral detail the annotations don't cover: the two-phase return behavior (transient state vs. final verdict plus content address and signing key). It doesn't mention polling cadence, terminal-state signaling, or failure/expiry behavior, which keeps it at 4 rather than 5.

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 short sentences, front-loaded with the core action, then lifecycle behavior, then a pointer to the sibling for the printable output. Nothing is redundant or padded.

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?

An output schema exists, so return values needn't be enumerated, yet the description still tells the agent what each phase yields and where the printable statement actually comes from. For a one-parameter polling tool, an agent has everything needed to invoke and interpret it.

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% and the single parameter's description already says it is 'the task_id returned by eudr_prepare_dds.' The description restates that provenance ('started by eudr_prepare_dds') but adds no format, lifetime, or reuse semantics, so the schema is doing the work.

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 (read the state) and resource (a compile started by eudr_prepare_dds), and names the originating sibling tool so the agent knows where the task_id comes from. It also implicitly separates itself from eudr_export_statement by pointing at the report_url for the printable statement.

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 two-phase framing ('while it runs… once finished…') clearly implies a polling pattern and tells the agent what to expect on each call. It stops short of stating explicitly that the tool should be called repeatedly until a terminal state, or naming rate/cadence expectations, so it's clear but not fully directive.

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