mark_human_approved

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

Without annotations, the description discloses that the tool writes a 'human_approval' sub-structure into the REVIEW frontmatter and returns the updated summary. It does not mention permissions or destructive actions, but covers the core behavior.

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 three sentences, front-loaded with the main purpose. It is concise, well-structured, and informative without extraneous words.

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 existence of an output schema and thorough input schema, the description provides sufficient context for the tool's workflow. It mentions the escalation loop and ADR-0026, leaving little ambiguity.

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 baseline is 3. The description adds minimal parameter details; it mentions the 'approver' must be an agent with layer admin, but this is already in the schema. No additional meaning beyond 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 records a human approval decision on a 'needs_human' REVIEW file, specifying the action and the context. It distinguishes from sibling tools like 'write_review' and 'read_review' by focusing on the approval step in the escalation loop.

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 indicates when to use: after a review has been set to 'needs_human' via 'write_review'. It provides clear context but does not explicitly state when not to use or mention alternative tools.

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