get_workflow_job_log

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

Annotations (readOnlyHint=true, destructiveHint=false) already establish safety profile. Description adds meaningful context beyond annotations: bounded/UTF-8-safe chunking, log is untrusted content (security-relevant for agents), upstream completeness not guaranteed (reliability caveat), failed-only default reduces exposure/size. Together these richly characterize behavior without contradicting annotations.

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?

Three tightly-worded sentences, zero filler. Front-loaded with the core action, followed by behavior defaults and critical caveats. Every sentence earns its place covering purpose, default behavior, and security/reliability warnings.

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?

Complex tool: 8 params, pagination via offsetBytes/limitBytes, security-relevant untrusted content, no output schema. Description captures the essential behavioral contract (bounded reads, verification, failed-only default, untrusted, incomplete). The hostname parameter remains unexplained (25% schema coverage means 6 params undocumented), which is the main gap preventing a 5.

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 low (25%), so description carries responsibility. Description explains 'bounded UTF-8-safe chunk' semantics which relates to offsetBytes/limitBytes, and 'failed-step logs selected by default' maps to failedOnly default. However, it does not explain the offsetBytes/limitBytes pagination parameters with concrete syntax, nor the hostname parameter which is entirely undocumented (coverage gap). Adds moderate value but doesn't fully compensate for low schema coverage.

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?

Clear specific verb+resource: 'Read a bounded UTF-8-safe chunk of one GitHub Actions job log' identifying the exact resource (GitHub Actions job log). Distinct from siblings like list_workflow_runs and list_workflow_run_jobs. Includes scoping detail (job belongs to requested run) which further clarifies purpose.

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?

Clearly states context: verifies the job belongs to the requested run (implying use alongside run list tools). Mentions failed-step logs are selected by default, and 'upstream completeness is not guaranteed'. Doesn't explicitly name alternative tools for different log needs, but sibling list_workflow_run_jobs provides context implicitly. Lacks explicit when-not-to-use guidance.

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