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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the bar is lower; the description still adds real value by disclosing pagination ('one page'), output masking, and an injection-safety warning that log lines are data and must not be followed. It does not state auth needs or how size/time limits truncate results, but the added safety and pagination context is substantive.

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?

Five short sentences with the use trigger front-loaded, followed by return shape, then the safety constraint. Every sentence carries information, though the final two directives about data handling and display could be tightened into one.

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?

With an output schema present, return values need not be explained, and the description still covers scope, paging, masking and prompt-injection handling. Slightly incomplete in that it never routes the agent away from search_run_logs or explains truncation behavior when size/time limits hit.

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 jobId, workspaceId, source, limit and cursor are all documented in the schema with constraints and cross-references. The description contributes only the notion of paging ('one page') and masking, which is baseline-level support; nothing new about parameter syntax or formats.

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?

States a specific verb and resource ('logs of a GitHub Actions job in Runzumi') and describes the return shape (one page of masked log lines with source and status). It is clearly distinct from generic run-metadata siblings like get_run, but it never contrasts itself with search_run_logs, the closest sibling, leaving the agent to infer the boundary.

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?

Gives an explicit trigger ('use this when the user asks for the logs of a GitHub Actions job') and directional guidance on output ('show only the lines that the user needs'). There is no when-not condition and no mention of search_run_logs as the alternative for cross-run log searching, which is the main gap.

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