read_result

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral context: the 1-hour retention window, the preview behavior, the credit cost, and the semantics of each operation (search, slice, lines, json_path). This goes beyond the annotations without contradicting them.

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 dense paragraph that front-loads the primary use case and ends with an example. It is somewhat lengthy but every sentence earns its place by covering scope, operations, exclusions, cost, and an example. A more structured layout could improve skimmability, but it remains 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 an output schema exists (not shown but present), the description need not detail return formats. It covers the main trigger, all operations, exclusions, cost, and handle validity. It does not explicitly mention error cases (e.g., expired handle), but the output schema likely handles those. Overall, it's sufficiently complete for correct 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 coverage is 100%, so every parameter is documented. The description adds operation-specific meaning (e.g., 'search finds a literal query with offsets and context', 'json_path reads one subtree') and a usage example that clarifies how parameters combine. This enriches understanding beyond the schema's basic field descriptions.

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 the tool reads truncated results, identifies the trigger condition (truncated: true with a result_handle), and explicitly distinguishes itself from fetching tools by instructing not to call the original tool again. It also names sibling tools indirectly and lists distinct operations, making its scope unambiguous.

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 explicit when-to-use (truncated results) and when-not-to-use (whole results, not a fetching tool) guidance. It also gives a concrete example call and notes the 1-hour handle validity, which helps the agent decide when to invoke this tool versus alternatives like fetch_url or crawl_deep.

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