console

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

With no annotations, the description carries the full behavioral disclosure burden. It goes beyond basic invocation by revealing that opening a console starts background capture immediately, that max_lines defaults to a huge buffer, and that view queries operate on the captured buffer rather than driver receive. These are meaningful behavioral traits not derivable from the schema, though it doesn't discuss close/send side effects or error 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 a single dense paragraph but is efficiently organized by operation with semicolon-separated sub-specifications. Every clause provides necessary information for a complex multi-op tool; however, some formatting (e.g., line breaks per op) could improve scanability without adding length.

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 tool has 16 parameters, no output schema, and multiple operation modes, the description is highly complete: it covers op-specific parameter requirements, default behaviors, and capture semantics. Minor gaps remain around return value shapes, error conditions, and lifecycle side effects, but for the tool's complexity, this is a strong profile.

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?

Despite 0% schema description coverage, the description names and contextualizes every parameter: op, path/device, baud, max_lines, id, data/data_b64, newline, mode, n, since, contains, context, settle_ms, with_seq, and sessions. It explains parameter combinations per operation and even specifies value vocabularies like mode=tail|since|contains. This fully compensates for the otherwise opaque 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 identifies the tool as a Serial Console for embedded device links, distinguishing it from PTY/SSH interfaces. It enumerates the specific operations (list, open, send, views, close, sessions) and their scopes, making the purpose unambiguous and differentiating it from sibling tools like 'screen' or 'exec'.

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 operation-specific usage instructions, including which parameters apply to each op and constraints like 'do not scan /dev or drivers' and 'queries capture buffer (not driver recv)'. It lacks explicit 'when to use vs alternatives', but the 'not PTY/SSH' and embedded-device context provide clear situational guidance.

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