get_transcript

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the tool is a non-destructive, rolling 256 KB record, and that it does not consume data (unlike read tools). It also notes the resource alias. It doesn't mention side effects, permissions, or error behavior, but the core behavior is well disclosed.

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 two short paragraphs, with the primary purpose front-loaded. It provides necessary detail about the rolling buffer and the alternative resource without redundancy. It could be slightly more compact, but it is efficient and well organized.

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?

The description explains the tool's behavior and use case well, but it omits parameter semantics and any prerequisites (e.g., a connection must exist). An output schema exists, so return format is covered, but the missing parameter documentation leaves the tool incomplete for an agent to call correctly without additional inference.

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 does not explain what 'connection' refers to (e.g., the connection name from connect) or how 'last_bytes' relates to the returned tail. The description implies a tail but leaves the parameters ambiguous. This is a significant gap given no schema-level documentation.

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 states a specific verb ('Return') and resource ('tail of everything received on a connection'), and clearly differentiates itself from read tools by highlighting the rolling buffer that persists regardless of consumption. This distinguishes it from siblings like read_available and read_until_prompt without needing to name them.

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 explains the primary use case: re-reading output that was already consumed or arrived between calls. It contrasts with 'read tools' generically but doesn't explicitly name alternatives or provide exclusion conditions. It also mentions an alternative access method via a resource, which adds useful context. However, it could be more explicit about when to use this over specific siblings.

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