ck_result_peek

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds behavioral details like byte-range reads, offset/peek_bytes usage, and the pattern, which are beyond what annotations provide. No contradictions.

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 concise (6 sentences), front-loaded with purpose, and every sentence adds value without fluff.

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 has an output schema and moderate complexity, the description covers usage pattern, parameter decisions, and relationship to ck_delegate, making it complete for agent use.

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%, but the description adds context on how to use parameters (e.g., 'pass peek_bytes to limit how much to load, and offset to skip ahead') and references result_ref/package_root from ck_delegate, adding meaning beyond the schema.

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's purpose: 'Peek at the full stdout of a previously completed ck_delegate embedded run without loading it all into context.' It specifies the action (peek), resource (stdout), and context (ck_delegate embedded run), distinguishing it from sibling tools like ck_delegate and ck_fs_read.

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 explains when to use (after ck_delegate completes, using result_ref and package_root) and how to decide (use result_length). It describes the RLM variable-encapsulation pattern. However, it does not explicitly state when not to use or compare to alternatives.

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