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

Annotations already indicate readOnly, idempotent, and non-destructive. The description adds significant behavioral context: 'This call does not run code' and 'execution uses loopback only and never uploads or publishes results.' This goes beyond the annotations and clarifies that the tool only returns source/instructions, not executing anything. It also describes the return contents (source URL, commands, requirements, report fields). 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?

The description is about five sentences, each carrying useful information: purpose, return fields, non-execution, execution constraints, and usage context. It is front-loaded with the primary purpose. It is not overly verbose but could potentially be tightened slightly by merging some sentences. Overall, it is well-structured and efficient.

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?

Given the tool's simplicity (no parameters, no output schema), the description covers all necessary aspects: what it returns, prerequisites (Python 3.9+, curl), safety (loopback only, no upload), and when to use it. It provides enough detail for an agent to decide whether to call it and what to expect, without needing additional schema or annotation information.

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?

The tool has zero parameters and the schema is empty with 100% coverage, so there is no parameter to document. The baseline for zero-parameter tools is 4. The description does not need to add parameter semantics, and it does not attempt to. It correctly focuses on behavior and usage.

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 clearly states a specific verb+resource: 'Get a downloadable localhost diagnostic for installed curl' and precisely defines the comparison being made (default vs --retry 1 against HTTP 429/503 with Retry-After headers). It distinguishes itself from siblings like create_retry_run (which likely executes runs) by explicitly stating 'This call does not run code', and from read_retry_finding (which reads results) by returning source and commands. This is unambiguous and differentiated.

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 provides a clear condition: 'Useful when a local fixture can answer the task without a remote diagnostic run.' It also explains the execution context (Python 3.9+, loopback only). However, it does not explicitly name an alternative tool for remote diagnostics, though sibling names like create_retry_run and read_retry_trace imply this. This is adequate context but lacks an explicit 'when not to use' statement naming the alternative.

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