compute.get_logs

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description goes beyond that by disclosing two behaviors the annotations do not: the output merges stdout and stderr, and it is redacted for secrets — an important caveat since an agent cannot rely on seeing full raw output. It stops short of describing truncation or failure behavior.

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?

A single sentence with no filler, front-loaded with the action and the resource, and parenthetically packing in the stdout/stderr and redaction details efficiently.

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 burden of describing the return value; it does say the output is combined, truncated log text redacted for secrets, which is decent. However, it never specifies what happens for an unknown run_id, whether a run must have started or completed, or the units/limits of the tail. For a simple two-parameter read tool this is adequate but leaves clear gaps.

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 schema gives no parameter meaning beyond titles and defaults. The phrase 'the tail of a run's log' implicitly conveys that the tail parameter bounds how much of the end of the log is returned, but neither the unit (lines), the default of 200, nor the run_id format is addressed. It partially compensates, so a 3.

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 (Read) and resource (the tail of a run's log) and clarifies that stdout and stderr are combined. It is clearly distinguishable from sibling tools like compute_get_run (metadata) or compute_get_run_progress, though it never names those alternatives explicitly.

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?

Usage is only implied: an agent can infer this is the tool for inspecting raw run output, presumably for debugging. There is no explicit when-to-use statement, no mention of when to prefer compute_get_run_progress or compute_collect_results instead, and no stated prerequisites such as run state or permissions.

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