agent_output

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

No annotations are provided, so the description carries the full burden. It discloses useful behavioral details: default 50 lines, max 200, and addressing by name or agent_id. However, it does not describe error behavior, what happens when no name/agent_id is passed, whether output is plain text, or how the rendered terminal is returned. Adequate but incomplete.

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 short sentences with no filler. The core action is front-loaded, key defaults are included, and the practical usage instruction is appended in a tight, memorable way. Every word earns its place.

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 simple read tool with no output schema and no annotations, the description gives the essential purpose and one key usage rule, but leaves gaps around return format, error conditions, and invocation without any address. It is workable but not fully self-sufficient.

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 75%, and the schema already documents name, agent_id, and project_id. The description adds the default line count and the 'name or agent_id' addressing concept, which supplements the schema for the 'lines' parameter. This is useful but not extensive, so a 3 is appropriate.

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 opens with a specific verb and resource: 'Read the rendered terminal of an agent,' which clearly identifies the tool's core function. The additional phrase 'addressed by name or agent_id' clarifies the addressing modes. It does not explicitly name a sibling alternative, but the purpose is distinct from nearby tools like agent_status or pad_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 instruction 'Read REAL output before declaring a worker done' gives an explicit when-to-use context that would help an agent know this is the verification step. It does not mention exclusions or alternatives, so it stops short of a 5, but the context is clear and actionable.

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