read_log_tail

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

With no annotations, the description fully carries the burden and does so richly. It discloses the paging budget logic (max_chars/lines), the self-referencing before_line mechanism for upward traversal, clipping behavior, and automatic log download. These are non-obvious behaviors critical for correct invocation.

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 dense yet efficient. It front-loads the purpose, then usage guidance, then parameter mechanics, with each sentence serving a distinct purpose. The note about different line counts adds practical value without redundancy.

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 complex paging tool, the description covers all necessary aspects: direction, budgets, paging technique, clipping, and auto-download. It also touches on the return format by describing the 'result ends with the exact call for the page above it', and the output schema exists to formalize the rest.

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 0%, so the description compensates entirely. It explains max_chars as the page-sizing budget, lines as a cap, before_line as the page boundary, and max_line_chars with clipping details. build_id and filename are self-evident from context, so no additional explanation is needed.

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 opening sentence, 'Read a page of a build log from the end, and page upward from there', states a specific verb, resource, and direction. It also explicitly contrasts itself with search_log ('To FIND a compile error, use search_log'), making its unique purpose clear.

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 explicitly tells when to use it ('Good for how the build terminated') and when not to ('To FIND a compile error, use search_log'). It also notes the prerequisite is handled automatically ('no need to call download_log first'), covering both usage context and alternatives.

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