terminal_read

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context beyond annotations: ANSI sanitization, cursor advancement over raw bytes, and the lease_id requirement. It doesn't cover all edge cases (e.g., retention limits, invalid lease behavior) but significantly enriches the safety profile provided by annotations.

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 concise sentences, front-loading the main action and then providing essential details in a logical order. Every sentence adds value—no repetition, filler, or unnecessary 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?

Given the output schema exists, return values don't need explanation. The description covers the core mechanics (cursor, lease, sanitization) and is well-aligned with annotations. It misses details about retention behavior and optional parameter roles, but for a read operation with strong annotations and schema, it's fairly complete.

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 0%, so the description must compensate. It explains 'cursor' and 'lease_id' explicitly, but leaves 'alias', 'pane_id', and 'max_bytes' unexplained. The parameter names are somewhat self-explanatory (e.g., max_bytes), but 'alias' and 'pane_id' could be ambiguous without further context. Partial compensation, but gaps remain.

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 function: 'Read incremental terminal output from the durable spool (pipe-pane).' This uses a specific verb (Read), identifies the resource (terminal output from durable spool), and distinguishes it from sibling tools like terminal_snapshot by emphasizing 'incremental' and 'pipe-pane.'

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 provides practical usage context: it explains cursor mechanics ('Pass next_cursor from the previous call; omit cursor to start at retained start') and the lease requirement. It doesn't explicitly contrast with alternatives like terminal_snapshot, but the 'incremental' vs. snapshot distinction is implied. This is clear guidance without formal exclusions.

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