task_log

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

Annotations provide readOnlyHint=true, so the safety profile is covered, and the description adds genuinely new behavior: the exact return payload shape, the truncation flag semantics, and the node-omission fallback that parses the node from the UPID. It stops short of describing pagination mechanics, auth requirements, or error behavior for an invalid UPID, which keeps it below 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?

The [READ] marker and purpose lead the description, followed by return shape and then args, so it is well front-loaded. Sentences are tight overall, though the truncation warning is slightly verbose relative to the rest and the Args block partly restates schema titles.

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?

There is no output schema, so the description carries the full burden of describing the response, and it does so precisely with the lines/returned/limit/truncated fields. Combined with annotations covering read-only safety and all four parameters being explained, an agent has everything needed to call and interpret this 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 description coverage is 0%, so the description must carry all parameter meaning and does document all four args. It adds real value beyond the bare names: 'target' is explained as coming from config and 'node' notes that omitting it parses the value from the UPID, plus the limit default of 200 in the schema is referenced. The per-arg notes are terse, so format expectations for upid/limit are only minimally clarified.

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 ('Fetch the log lines of an async task') plus the identifier scope (by its UPID). This clearly separates it from sibling task_status, which reports task state rather than log output, so an agent can pick between them without opening a schema.

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 real operational guidance for truncated results ('raise limit or narrow the query rather than assuming you have the whole log'), which tells the agent how to interpret and react to output. However, it never states when to use this tool versus task_status or any other sibling, and offers no prerequisites or exclusions, leaving tool selection to inference.

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