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

readOnlyHint=true already covers the safety profile, and "read-only" largely repeats it. The added value is the "Free" cost note and the two invocation modes, but it says nothing about freshness, retention, or rate limits. Adequate addition over annotations, not rich.

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?

Two tightly packed sentences with zero waste: purpose and use cases first, invocation modes second. Nothing is filler.

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 no output schema, the description usefully summarizes the log line shape and both calling paths, which is enough to invoke it. It omits the range/limit behavior and any fetch window, a minor gap for a read-only diagnostic tool.

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 only 50% (limit and projectId undocumented), yet the description supplies the key fact the schema omits: that projectId + service (default "web") and machineId are alternatives ("or"). This clarifies mutual exclusivity and the service default. The limit parameter remains unexplained.

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+resource (log lines of a server and its builds) and even names the returned fields (time, level, message). It is clearly distinguishable from siblings like get_errors, check_health, and compute_build_status.

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 concrete triggering scenarios — debugging a failed build, a crash, or a wrong port. It lacks explicit when-not guidance or routing to an alternative diagnostic sibling such as get_errors, but the use context is unambiguous.

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