ssh_tail

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

With no annotations provided, the description carries full burden. It discloses that the tool is read-only, that 'follow' mode streams output to stderr and returns only a session note, and that setting follow=false returns the last N lines. This covers the key behavioral nuance and potential side-effect (output not returned in follow mode). It could mention error handling or server prerequisites, but overall it is transparent.

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 sentences that efficiently convey purpose, read-only guarantee, and crucial parameter behavior. It is front-loaded with the core action. While it could be more structured (e.g., bullet points for modes), every sentence earns its place and no information is redundant.

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 no output schema, the description explains what the tool returns in each mode (content in follow=false, session note in follow=true). It covers the main parameters and their implications. It does not discuss error handling, authentication, or server configuration, but the context from sibling tools and common usage patterns suggests these are covered elsewhere. The description is complete enough for an agent to use the tool correctly.

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 coverage is 100%, so baseline is 3. The description adds value by explaining the semantics of 'follow' (streaming vs static), the default value for 'lines' (10), and the effect of 'grep' filtering. This goes beyond the schema's property descriptions, which only note defaults. The description also clarifies the response behavior dependent on 'follow'.

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 action: 'Reads the tail of a remote log file'. It clearly identifies the resource (log file on a named server) and the operation (tail with optional grep filter). This distinguishes it from sibling tools like ssh_execute which could run arbitrary commands, making its purpose unambiguous.

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 that the tool is read-only and does not modify remote state, guiding when to use it. It provides critical context on the 'follow' parameter behavior, recommending setting follow=false to capture output directly. However, it does not explicitly name alternative tools for similar tasks, such as consulting logs via ssh_execute or other means.

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