agent_output

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

Annotations already declare idempotentHint=true and destructiveHint=false, consistent with the 'read' framing. The description adds the line-window defaults and the 'verify real output before declaring done' workflow cue, but says nothing about what the rendered terminal contains or how it behaves when the agent has exited. readOnlyHint=false is conservative and sits in mild tension with 'Read', though destructiveHint=false and idempotentHint=true keep them reconcilable.

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?

Two sentences, no filler, with the operation and its size bounds front-loaded before the usage cue. Every clause carries information an agent needs.

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 tool with no output schema and well-annotated parameters, the description covers operation, addressing, and window size adequately. It would be complete at 5 if it hinted at the returned content (text lines) or the empty/partial-name edge case beyond what the schema says.

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 75%, so the schema already explains name/agent_id precedence and the project_id scoping rule. The description contributes the one thing the schema omits: the default line count of 50 against the schema's max of 200, plus the name-or-id addressing summary.

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?

States a specific verb and resource ('Read the rendered terminal of an agent') with concrete bounds (default 50 lines, max 200), which is far more specific than the bare name. It implicitly separates itself from agent_list/agent_status by being about output content, but it never names a sibling to differentiate against, so it stops short of a 5.

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?

'Read REAL output before declaring a worker done' gives a concrete trigger for use rather than relying on agent status alone. There is no explicit when-not-to-use or named alternative tool, so it is clear context without exclusions.

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