File tail

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

The description truthfully states the core behavior and does not contradict the readOnlyHint annotation. It adds little behavioral context beyond that already provided by annotations, such as error behavior, line-ending handling, or the default line count, but for a simple read-only tool the annotation covers the main safety profile.

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?

A single, clear, front-loaded sentence with no filler. Every word contributes to explaining the tool's purpose and behavior.

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?

For a simple read-only tool with an output schema, a required path, and a lines parameter with a default, the description is sufficient. The schema and annotations cover defaults and safety, so nothing essential is missing for an agent to invoke it 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 description coverage is 0%, so the description must carry meaning for the parameters. It does map 'file' to path and 'N' to lines, which is helpful, but it omits the default value of 50, the required status of path, and any constraints on the lines integer. It compensates partially, not fully.

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 uses a specific verb ('Return') with a clear resource ('last N lines of a file'), which fully communicates what the tool does. It inherently distinguishes itself from sibling tools like head_file and read_file by specifying tail semantics.

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 implies the use case: when you need the tail end of a file. However, it does not explicitly mention alternatives or exclusion conditions, such as 'use head_file for the first N lines' or 'use read_file for full contents', so routing guidance is only implicit.

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