serial_output_history

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral value by disclosing the mode-dependent return shapes (JSON cursor page with cursor/dropped/has_more/chunks vs prose by time/bytes), which annotations cannot convey.

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?

Four front-loaded fragments with zero filler, and the non-destructive framing leads. It is dense to the point of being terse, but every clause carries information.

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?

With no output schema, the description does the work of describing both return formats (JSON cursor page vs prose), and the four params are fully covered by the schema. Adequate for a read-only history tool, though it could note pagination/cursor-reuse behavior more explicitly.

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 100%, so the schema already documents all four parameters in detail. The description only echoes the since_seq vs time/bytes split already present in the schema, adding no syntax or format nuance beyond it.

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 resource (history) and a defining trait (non-destructive), and names the sibling it is not by noting 'serial_read is drain-only'. The agent can tell this retrieves past output rather than draining it, though the phrase 'Non-destructive history' never literally says 'serial output' and leans on the tool name for context.

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?

Gives clear mode-selection guidance: 'With since_seq' yields a cursor page while 'Without' yields prose by time/bytes. The contrast with serial_read ('drain-only') implies when to prefer this tool for non-destructive retrieval, but it stops short of an explicit when-not-to-use rule.

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