job_log

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

With no annotations present, the description carries the full behavioral burden and does real work: it discloses the 100000-byte response bound, the 10 MiB saved-log cap, cursor continuability via next_offset, and the important nuance that at_end means caught up with observed bytes rather than completed slicing. It omits error behavior (invalid job_id, out-of-range offset) and permission requirements, keeping it from a 5.

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?

Three short sentences with zero filler, and the core action plus cursor-reuse rule is front-loaded. The final sentence about at_end earns its place by preventing a plausible misreading of the output.

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?

An output schema exists, so return-value shape need not be explained, and the description covers the pagination and size semantics an agent needs to call this correctly. The remaining gap is error and precondition behavior for a tool with no annotations to cover it.

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% across three parameters, so the description must compensate. It clarifies that offset is a byte cursor and that next_offset should be reused, which adds meaning beyond the schema. But it never mentions job_id or limit_bytes, and the relationship between the 8000-byte default limit and the 100000-byte response bound is left ambiguous.

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 verb and resource: 'Read saved CLI output from a byte cursor.' That is clearly distinct from job_status, job_wait, and jobs_list, which manage job lifecycle rather than log retrieval. It stops short of explicitly naming those siblings, so it lands at 4 rather than 5.

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?

'reuse next_offset on reconnect' gives a concrete usage hint for continuing a read, which is genuinely actionable. However, there is no statement of when to choose job_log over job_status or job_wait, nor any prerequisite or exclusion. Usage is implied rather than guided.

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