Read the log of a DataLens Spark application

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, so the safety/behavior profile is mostly covered. The description adds pagination semantics (fragment + nextPageToken) which the annotations don't convey. The honest caveat that the API is 'Experimental...not measured' is useful transparency, but no info on rate limits, log retention, or truncation behavior of fragments.

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 sentences, front-loaded with the return format and then the continuation instruction. Minimal waste, though the 'Experimental...written from its document: not measured' caveat is awkward and mid-sentence; a cleaner phrasing would lose nothing.

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 paginated read with annotations covering the safety profile and a fully described schema, the essentials are present. But there's no output schema, and the description doesn't say what a fragment's log content looks like or how to detect end-of-log, which an agent needs to correctly loop pagination. Adequate but with a clear gap.

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 100%, so cluster_id, application_id, page_size, and page_token are all documented in the schema. The description restates the page_token usage which the schema already covers ('the token of the fragment to read'), so no meaningful value is added beyond the schema. Baseline 3 applies.

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 names the resource (an application's log) and the key behavior (returns one fragment plus a continuation token). It's clear this is a paginated log-read, and the sibling set contains no other log-reading DataLens tool, so differentiation is implicit rather than stated. The 'fragment' framing is slightly unusual but functional.

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?

The description tells the agent how to continue pagination ('Give nextPageToken back as page_token to read on'), which is useful usage guidance. However, it gives no when-to-use guidance relative to alternatives (e.g., sparkapplications_get, sparkapplications_list), no mention of when the log is unavailable, and no handling guidance for the last page.

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