job_retry

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

With no annotations provided, the description fully carries the burden. It discloses that it is a WRITE operation, runs asynchronously, and retries only failed objects. It does not mention permissions or rate limits, but the behavioral traits are adequately covered.

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?

The description is concise, well-structured, and front-loaded. The initial line states the core purpose, followed by usage guidance and parameter list. No extraneous information.

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?

The description covers key aspects: purpose, async nature, how to monitor, inverse action, and parameters. It does not elaborate on error conditions or edge cases, but it is fairly complete for a tool with moderate complexity and no output schema.

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%, but the description adds meaningful explanations for both parameters: job_id ('Veeam job id') and target ('Veeam target name from config'). This compensates fully for the lack of schema descriptions.

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 clearly states the verb (Retry), the resource (a failed backup job), and adds specificity (re-runs failed objects only). It distinguishes from sibling tools like job_start which would run a full job, and job_stop which cancels the retry.

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 provides explicit guidance on how to monitor the async session using session_list/session_get and identifies job_stop as the inverse action. It implies when to use (for failed jobs) but does not explicitly state when not to use it or compare to alternatives like job_start.

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