job_status

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

With no annotations, the description carries the full burden. It does add real behavioral facts beyond the schema: the state is durable (persisted across restarts) and the log tail is bounded. It says nothing about behavior for unknown/expired job ids, blocked vs. non-blocking reads, or truncation of output files.

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?

One front-loaded sentence with three high-density clauses and zero filler. Nothing to trim and nothing buried.

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?

An output schema exists, so return-value explanation is legitimately omitted, and the two-parameter surface is small. Still, for a tool with five adjacent job_* siblings and zero schema descriptions, the definition leaves the selection decision and parameter meaning under-specified.

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 0%, so the description must compensate. 'Bounded log tail' hints that log_tail_bytes caps the returned tail, but job_id's expected format and semantics are never explained, and no defaults or units are mentioned in the prose.

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?

Specific verb (Read) plus concrete resources (durable job state, output files, log tail) tell an agent exactly what comes back. It does not, however, distinguish itself from close siblings like job_log, job_wait or jobs_list, leaving the boundary to inference.

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?

No guidance on when to use this versus the many job_* siblings. An agent cannot tell from the text whether to call job_wait to block, job_log for full logs, or this tool for a status snapshot; only the presence of a required job_id implies the polling scenario.

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