llm_request_result

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds useful context about the flight-recorder source, sync/async coverage, and the local-only job-record behavior. However, claiming the read-back includes 'prompt and response' is ambiguous or potentially misleading because includePrompt defaults to false, and maxChars truncation is not mentioned.

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 a single sentence that front-loads the action, identifies the lookup key, mentions scope (sync/async), and includes the key local/remote caveat. There is no filler, tautology, or redundant restatement of schema fields.

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 read-only tool with strong annotations and a fully described input schema, the description gives enough context to invoke it correctly: source, correlationId lookup, sync/async coverage, and the local-only job-record option. The lack of an output schema makes the ambiguous 'including prompt and response' wording more noticeable, but overall the core contract is clear.

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 100% and each parameter already has a meaningful, self-contained description. The tool description adds high-level context but does not materially deepen the semantics of correlationId, maxChars, includePrompt, or includeJobRecord beyond the schema, so baseline 3 applies.

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 uses a specific verb ('read back') and a concrete resource ('persisted request ... from the flight recorder by correlationId'). It clearly covers sync/async requests, prompt/response content, and the local-only job-record option, which separates it from list/status tools like llm_request_list or llm_job_result.

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 clearly frames the tool as a by-correlationId lookup for persisted flight-recorder requests, and it notes the local vs remote caller distinction. It does not explicitly name alternatives or state when not to use it, so it stops short of full routing guidance.

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