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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds latency ('inference can take several minutes') and a strong behavioral warning ('Never fake ready results'), but omits auth needs, rate limits, or error handling details.

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, front-loaded with the main action, and no filler. The second sentence is a clear directive. Slightly under-specified rather than verbose.

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 simple read-only polling tool with annotations covering safety, the description covers what it does and a key behavioral caveat. However, it leaves parameter meaning, return-value expectations, and relationship to start_analysis unexplained, which an agent would need for reliable invocation.

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 0% for both required parameters (workspace_token, analysis_id), and the description does not mention them at all. The agent receives no semantic guidance on what these fields expect or how to obtain them.

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 says 'Poll GPU status and delivery gates', which gives a verb and some objects, but it never states that it retrieves analysis results or how it differs from start_analysis. An agent can infer it is a status-checking tool but cannot confidently distinguish its purpose from siblings.

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 phrase 'Poll GPU status' implies repeated checking, but there is no explicit when-to-use guidance, no exclusions, and no mention of alternatives (e.g., start_analysis, get_scan). The warning 'Never fake ready results' is a behavioral rule, not usage routing.

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