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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds real value beyond that: logs are 'persisted', returned 'oldest first', and pagination flows through nextPageToken/page_token, which an agent needs to avoid mis-reading the result set.

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?

Front-loaded with the purpose, then routing, then pagination in three tight sentences with no filler. The trailing 'Depot: CIService/GetJobAttemptLogs' identifier is mild overhead but arguably useful for tracing.

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?

With no output schema, the description compensates by naming the returned line fields (step key/name, timestamp, line number, body) and explaining the pagination cursor. Complete enough for correct invocation, though it omits any statement about maximum page size or truncation behavior.

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 100%, so the baseline is 3. The description goes beyond the schema by stating the mutual-exclusion rule ('exactly one' of job_id/attempt_id) and by tying nextPageToken to the page_token parameter, which the schema does not express.

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 ('Get persisted log lines for a Depot CI job attempt') plus ordering and returned fields. An agent can distinguish it from log-adjacent siblings like depot_gha_search_logs and depot_get_build_step_logs without opening either 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 clear selection guidance for the two lookup modes ('Pass job_id to read the job's latest attempt, or attempt_id for a specific one — exactly one') and tells the agent to pass nextPageToken back as page_token. It does not contrast the tool against sibling log tools, but the internal routing guidance is explicit.

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