Download Task Run Log

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

readOnlyHint already marks this as a safe read, and the description adds meaningful behavior beyond that: base64 encoding of the payload and a hard 3MiB per-call content cap with a chunking workaround. It does not state whether the log must exist or what happens on an out-of-range request, but the disclosure is well above the annotations alone.

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 tight sentences: the core action plus return format first, then the size constraint and chunking mechanic. No filler, and the most decision-relevant constraint (3MiB cap) is front-loaded.

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 read-only download with no output schema, the description covers encoding, size limits, and paging, which is what an agent needs to call it correctly. The gap is provenance of the three required IDs and the distinction from the artifact/log-listing siblings.

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 20% (just account_id documented), so the description carries real burden and it does explain range_header semantics and syntax with the byte-range example. It says nothing about filename, task_run_id, or pipeline_run_id (three required IDs), leaving those entirely to inference.

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 ('Download a task run log file') plus the return encoding ('base64-encoded'), which is a genuine fact the agent needs. It does not, however, distinguish itself from near-neighbor siblings like download_task_run_artifact or list_task_run_logs, so the agent must 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?

It gives real operational guidance for the chunking case (3MiB ceiling, advance range_header each call with a concrete example), which is implied usage for large files. It offers no when-to-use guidance relative to list_task_run_logs or download_task_run_artifact, so the routing decision is left to inference.

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